https://lcg.in2p3.fr/api.php?action=feedcontributions&feedformat=atom&user=Lanconelcgwiki - Contributions [en]2026-06-10T13:37:30ZContributionsMediaWiki 1.43.1https://lcg.in2p3.fr/index.php?title=Atlas:Analysis_Challenge-STsummary&diff=4623Atlas:Analysis Challenge-STsummary2008-12-18T14:11:43Z<p>Lancone: /* Test 82 (Dec 15-17) */</p>
<hr />
<div>=== Target and metrics ===<br />
* Nb of events : Few hundred up to 1000 jobs/site <br />
* Rate (evt/s) : up to 15 Hz <br />
* Efficiency (success/failure rate) : 80 %<br />
* CPU utilization : CPUtime / Walltime > 50 %<br />
== Monitoring ==<br />
* CPU/Walltime and events/second plots are only measured with respect to the athena execution time. Athena setup, data preparation and data stageout are <b>not</b> included in this. <br />
* Mean Athena Software Setup Time, Mean Prepare Inputs Time and Mean Output Storage Time are in seconds<br />
** Mean Athena software : time measured from the start of ganga worker node script until data preparation (Athena distribution kit setup, unpacking of the tarball with the pre-compiled code and setup of the pre-compiled code.<br />
** Mean Prepare Inputs Time covers LFC bulk access, one lcg-gt call for dCache/castor or multiple lcg-gt calls for DPM for turl retrieval <br />
** Mean Output Storage Time : call of lcg-cr<br />
<br />
== To be tracked, open questions ==<br />
* GRIF : dealing with a multi-site : Is it possible to stress GRIF site by site ? <br />
* Distribution of datasets over sites for stress test purposes (Is it possible to improve ?) <br />
* lcg-gt timeout (jobs in running state observed at LPC & CPPM) (not in Tokyo ??? so what ?)<br />
* Corrupted AOD files <br />
* rfio tuning (read-ahead buffer size) needed or not at some sites<br />
* many problems identified but no real stress so no clear bottlenecks identified at sites for now...2009 plans ?<br />
* comparaison and understanding of job timing (Athena software time discrepancy)<br />
<br />
== Test 82 (Dec 15-17) ==<br />
* http://gangarobot.cern.ch/st/test_82/ <br />
300 jobs scheduled - 10 sites involved : IN2P3-CC, LPC, GRIF-LAL, GRIF-SACLAY, GRIF-LPNHE, IN2P3-LAPP, TOKYO-LCG2, RO-02, RO-07, IN2P3-CPPM <br />
* Summary :<br />
28 jobs sent to IN2P3-LAPP <br><br />
42 jobs sent to RO-07-NIPNE <br><br />
45 jobs sent to RO-02-NIPNE <br><br />
74 jobs sent to IN2P3-CPPM <br><br />
237 jobs addressing GRIF-SACLAY but run at LAL <br><br />
238 jobs sent to IN2P3-LPC <br><br />
247 jobs sent to GRIF-LPNHE <br><br />
300 jobs addressing GRIF-LAL - some run at IPNO <br> <br />
300 jobs sent to IN2P3-CC<br><br />
300 jobs sent to TOKYO-LCG2 <br><br />
- <b>LAPP</b> 28 jobs sent there - no dataset available to stress the site <br />
- <b>LPC</b> half of the input files processed <br />
Seen in [http://gangarobot.cern.ch/st/test_82/gangadir/workspace/gangarbt/LocalAMGA/5/178/output/stderr.gz job 178 (competed) stderr]<br />
file rfio://clrgpfssrv03-dpm.in2p3.fr//storage/atlas1/atlas/2008-10-20/<br />
AOD.026982._00003.pool.root.1.2356089.0 <br />
can not be opened for reading (Timed out)<br />
failed jobs with error reading file from clrgpfssrv03-dpm.in2p3.fr<br />
Connection reset by peer - Connection closed by remote end<br />
37 % of jobs remained in running state - <br />
job blocked reading file observed at LPC (JCC) and CPPM (EK) - <br />
(stderr) send2nsd: NS009 - fatal configuration error: Host unknown: <br />
dpnshome.in2p3.fr<br />
wrong turl pattern 'rfio:/dpm/in2p3.fr/home/atlas/atlasmcdisk/mc08..' <br />
probably due to lcg-gt timeout<br />
- <b>CPPM</b> jobs remained in running state with wrong turl pattern <br />
probably due to lcg-gt timeout <br />
job.50 failure due to the corrupted AOD AOD.027076._10514.pool.root <br />
File: rfio:marjoe.in2p3.fr/../AOD.027076._10514.pool.root.1.3258341.0 badread=0<br />
- <b>GRIF-LPNHE</b>Problem (user mapping misconfiguration) identified <br />
GRIF UNSCHEDULED/DOWNTIME<br />
- <b>GRIF-SACLAY</b> 6 batch queues in GANGA jdl <br />
3 CES polgrid, grid10.lal, node07.cea <br />
all jobs supposed to be run at SACLAY were in fact executed at LAL <br />
with inputs taken from SACLAY SE and outputs written on LAL SE. <br />
Good test of 5 Gb/s link between SACLAY and LAL but we miss the ST<br />
of GRIF-SACLAY <br />
- <b>GRIF-LAL</b> : 8 batch queues in GANGA jdl<br />
4 CES : polgrid, grid10.lal, node07.cea, ipnls. <br />
Difference with SACLAY ? some jobs ran at IPNO <br />
Not all files being processed <br />
Job 8.19 DS mc08... Expected 999, Processed 334<br />
Seen in [http://gangarobot.cern.ch/st/test_82/gangadir/workspace/gangarbt/LocalAMGA/8/19/output/stderr.gz stderr Job 19] (completed) <br />
file rfio://grid19.lal.in2p3.fr//... can not be opened for reading (Bad credentials)<br />
- <b>CCIN2P3</b> 3 CES (2 from T2 and 1 from T1) in GANGA jdl<br />
jobs ran on cclclgceli05, cclclgceli06, cclclgceli01 why ?<br />
Overall jobs over time shows 140 jobs have started almost immediately <br />
the remaining ones have been queued for 16 hours <br />
<b> CC Toplevelbdii problem on Dec 15th by the end of the day <br />
+ one CE failure at T2</b> Effect on ST ? <br />
job 36 . failure due to corrupted AOD File: AOD.027076._10514.pool.root<br />
+ AThena core dump<br />
- <b>CPU/Walltime</b><br />
most of the sites at ~30% except LAPP&Tokyo (~60%)<br />
and SACLAY because jobs ran at LAL and input at Sacay<br />
LPC : 2 bumps?<br />
- <b>rfio</b> Pbs at LPC and some other sites (number of treated files <> number of expected files)<br />
no problem at CPPM this time<br />
- <b>ATHENA setup time</b> longer time at LAL<br />
- <b>Storage time</b>time of lcg-cr command, large differences between sites, to be understood<br />
<br />
== Test 61 & 62 (Dec 8-10) ==<br />
* http://gangarobot.cern.ch/st/test_61/ <br />
* http://gangarobot.cern.ch/st/test_62/ <br />
300 jobs : IN2P3-LPC, GRIF-LPNHE, IN2P3-CPPM <br><br />
600 jobs : TOKYO <br><br />
Input DS Patterns: <br />
mc08.*Wmunu*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*Zprime_mumu*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*Zmumu*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*T1_McAtNlo*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*H*zz4l*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*.recon.AOD.e*_s*_r5*tid*<br />
<br />
* Summary:<br />
- <b>TOKYO</b> reached the target : 15 evt/s - CPU/Walltime > 60 %<br />
only 3 jobs failure due to Athena crashes out of 600 jobs run<br />
Corrupted input AOD files found<br />
test 61, job 170, AOD.027097._37998.pool.root <br />
test 62, job 202, AOD.027579._24654.pool.root <br />
test 62, job 212, AOD.027076._10514.pool.root<br />
max. MySQL connections increased from 100, default, up to 200<br />
- <b>LPC</b>: 218 jobs (92.4 %) completed but not all input files could be read<br />
Number of input files processed by "completed" jobs ~29000 out of 58326 <br />
(expected to be)<br />
Site events/s less than 5 Hz - CPU/Walltime < 50 %<br />
Job 1.54, DS mc08.105001.pythia_minbias.recon.AOD.e357_s462_r541_tid027069): Expected 1000, Processed 4<br />
input files are available on disk <br />
rfio timeout seen in corresponding stderr<br />
rfio://clrgpfssrv03-dpm.in2p3.fr//storage/atlas1/atlas/2008-10-20/<br />
AOD.027069._03005.pool.root.1.2344130.0 can not be opened for reading<br />
(Timed out)<br />
<b>Possible work-around to be considered as applied in UK cloud</b> <br />
rfio tuning - increase of rfio bufsize on WNs <br />
See http://northgrid-tech.blogspot.com/2008/12/rfio-tuning-for-atlas-analysis-jobs.html<br />
- <b>CPPM</b>: <br />
Only 69 jobs sent because input datasets were unvalaible there<br />
27 failed jobs (no stdout, no stderr, did not even reach the CE) with<br />
the error message 'request expired' from WMS because of 'BrokerHelper:<br />
no compatible resources' (WMS log added to the monitoring page).<br />
This is seen sometimes by SAM ops test<br />
About 14 jobs remained in running state - seen running by site - doing<br />
nothing after 1 hour then killed by the batch scheduler<br />
no output/no logs = no clear disgnosis <br />
CPPM is using GRIF Topbdii. Impact of this ?<br />
<b>Decision taken to try to redistribute DS to Marseille to get more jobs <br />
but unsuccesfully </b><br />
- <b>GRIF-LPNHE</b> 1/3 of jobs remained in running state - seen then<br />
killed by the batch scheduler - no outputs/no logs = no clear disgnosis<br />
<br />
== Test 43 (November 28) ==<br />
* http://gangarobot.cern.ch/st/test_43/ 200 jobs over 12 sites<br />
* Problems seen : <br />
- Missing ATLAS release 14.2.20 @ CPPM <br />
<span style="color:green;">02/12/08 [DONE] validate-prod of 14.2.20 at marce01.in2p3.fr (IN2P3-CPPM)</span><br />
- Mapping CE-SE@GRIF-LAL and GRIF-SACLAY : Publication of multiple CloseSEs<br />
by LAL and IRFU cf https://savannah.cern.ch/bugs/index.php?44824<br />
<span style="color:green;">should be SOLVED by Ganga team</span><br />
- LFC bulk reading...End of LFC bulk reading...ERROR: Dataset(s)...is/are<br />
empty at GRIF-SACLAY_MCDISK / LAL_MCDISK <br />
(could be related to same problem)<br />
- ERROR@RO7-NIPNE : failed jobs with Athena errors <br />
http://gangarobot.cern.ch/st/test_43/gangadir/workspace/gangarbt<br />
/LocalAMGA/11/1/output/stdout.gz<br />
Core dump reading AOD file <br />
error reading from file rfio:tbit00.nipne.ro//storage1/atlas/2008-11-12/<br />
AOD.026357._00299.pool.root.1.810634.0 (Timed out)<br />
<span style="color:orange;">to be TRACKED</span> <br />
- NON FATAL ERRORS (completed jobs) @RO7-NIPNE, RO2-NIPNE : related to<br />
ATLASUSERDISK space token configuration<br />
ERROR during execution of lcg-cr --vo atlas -s ATLASUSERDISK<br />
ERROR: file not saved to RO-07-NIPNE_USERDISK in attempt number 3 ...<br />
ERROR: file not saved to RO-07-NIPNE_USERDISK - using now IN2P3-CC_USERDISK<br />
<span style="color:green;">CORRECTED</span></div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:Analysis_Challenge-STsummary&diff=4622Atlas:Analysis Challenge-STsummary2008-12-18T14:10:31Z<p>Lancone: /* Test 82 (Dec 15-17) */</p>
<hr />
<div>=== Target and metrics ===<br />
* Nb of events : Few hundred up to 1000 jobs/site <br />
* Rate (evt/s) : up to 15 Hz <br />
* Efficiency (success/failure rate) : 80 %<br />
* CPU utilization : CPUtime / Walltime > 50 %<br />
== Monitoring ==<br />
* CPU/Walltime and events/second plots are only measured with respect to the athena execution time. Athena setup, data preparation and data stageout are <b>not</b> included in this. <br />
* Mean Athena Software Setup Time, Mean Prepare Inputs Time and Mean Output Storage Time are in seconds<br />
** Mean Athena software : time measured from the start of ganga worker node script until data preparation (Athena distribution kit setup, unpacking of the tarball with the pre-compiled code and setup of the pre-compiled code.<br />
** Mean Prepare Inputs Time covers LFC bulk access, one lcg-gt call for dCache/castor or multiple lcg-gt calls for DPM for turl retrieval <br />
** Mean Output Storage Time : call of lcg-cr<br />
<br />
== To be tracked, open questions ==<br />
* GRIF : dealing with a multi-site : Is it possible to stress GRIF site by site ? <br />
* Distribution of datasets over sites for stress test purposes (Is it possible to improve ?) <br />
* lcg-gt timeout (jobs in running state observed at LPC & CPPM) (not in Tokyo ??? so what ?)<br />
* Corrupted AOD files <br />
* rfio tuning (read-ahead buffer size) needed or not at some sites<br />
* many problems identified but no real stress so no clear bottlenecks identified at sites for now...2009 plans ?<br />
* comparaison and understanding of job timing (Athena software time discrepancy)<br />
<br />
== Test 82 (Dec 15-17) ==<br />
* http://gangarobot.cern.ch/st/test_82/ <br />
300 jobs scheduled - 10 sites involved : IN2P3-CC, LPC, GRIF-LAL, GRIF-SACLAY, GRIF-LPNHE, IN2P3-LAPP, TOKYO-LCG2, RO-02, RO-07, IN2P3-CPPM <br />
* Summary :<br />
28 jobs sent to IN2P3-LAPP <br><br />
42 jobs sent to RO-07-NIPNE <br><br />
45 jobs sent to RO-02-NIPNE <br><br />
74 jobs sent to IN2P3-CPPM <br><br />
237 jobs addressing GRIF-SACLAY but run at LAL <br><br />
238 jobs sent to IN2P3-LPC <br><br />
247 jobs sent to GRIF-LPNHE <br><br />
300 jobs addressing GRIF-LAL - some run at IPNO <br> <br />
300 jobs sent to IN2P3-CC<br><br />
300 jobs sent to TOKYO-LCG2 <br><br />
- <b>LAPP</b> 28 jobs sent there - no dataset available to stress the site <br />
- <b>LPC</b> half of the input files processed <br />
Seen in [http://gangarobot.cern.ch/st/test_82/gangadir/workspace/gangarbt/LocalAMGA/5/178/output/stderr.gz job 178 (competed) stderr]<br />
file rfio://clrgpfssrv03-dpm.in2p3.fr//storage/atlas1/atlas/2008-10-20/<br />
AOD.026982._00003.pool.root.1.2356089.0 <br />
can not be opened for reading (Timed out)<br />
failed jobs with error reading file from clrgpfssrv03-dpm.in2p3.fr<br />
Connection reset by peer - Connection closed by remote end<br />
37 % of jobs remained in running state - <br />
job blocked reading file observed at LPC (JCC) and CPPM (EK) - <br />
(stderr) send2nsd: NS009 - fatal configuration error: Host unknown: <br />
dpnshome.in2p3.fr<br />
wrong turl pattern 'rfio:/dpm/in2p3.fr/home/atlas/atlasmcdisk/mc08..' <br />
probably due to lcg-gt timeout<br />
- <b>CPPM</b> jobs remained in running state with wrong turl pattern <br />
probably due to lcg-gt timeout <br />
job.50 failure due to the corrupted AOD AOD.027076._10514.pool.root <br />
File: rfio:marjoe.in2p3.fr/../AOD.027076._10514.pool.root.1.3258341.0 badread=0<br />
- <b>GRIF-LPNHE</b>Problem (user mapping misconfiguration) identified <br />
GRIF UNSCHEDULED/DOWNTIME<br />
- <b>GRIF-SACLAY</b> 6 batch queues in GANGA jdl <br />
3 CES polgrid, grid10.lal, node07.cea <br />
all jobs supposed to be run at SACLAY were in fact executed at LAL <br />
with inputs taken from SACLAY SE and outputs written on LAL SE. <br />
Good test of 5 Gb/s link between SACLAY and LAL but we miss the ST<br />
of GRIF-SACLAY <br />
- <b>GRIF-LAL</b> : 8 batch queues in GANGA jdl<br />
4 CES : polgrid, grid10.lal, node07.cea, ipnls. <br />
Difference with SACLAY ? some jobs ran at IPNO <br />
Not all files being processed <br />
Job 8.19 DS mc08... Expected 999, Processed 334<br />
Seen in [http://gangarobot.cern.ch/st/test_82/gangadir/workspace/gangarbt/LocalAMGA/8/19/output/stderr.gz stderr Job 19] (completed) <br />
file rfio://grid19.lal.in2p3.fr//... can not be opened for reading (Bad credentials)<br />
- <b>CCIN2P3</b> 3 CES (2 from T2 and 1 from T1) in GANGA jdl<br />
jobs ran on cclclgceli05, cclclgceli06, cclclgceli01 why ?<br />
Overall jobs over time shows 140 jobs have started almost immediately <br />
the remaining ones have been queued for 16 hours <br />
<b> CC Toplevelbdii problem on Dec 15th by the end of the day <br />
+ one CE failure at T2</b> Effect on ST ? <br />
job 36 . failure due to corrupted AOD File: AOD.027076._10514.pool.root<br />
+ AThena core dump<br />
-<b>CPU/Walltime</b><br />
most of the sites at ~30% except LAPP&Tokyo (~60%)<br />
and SACLAY because jobs ran at LAL and input at Sacay<br />
LPC : 2 bumps?<br />
-<b>rfio</b> Pbs at LPC and some other sites (number of treated files <> number of expected files)<br />
no problem at CPPM this time<br />
-<b>ATHENA setup time</b> longer time at LAL<br />
-<b>Storage time</b>time of lcg-cr command, large differences between sites, to be understood<br />
<br />
== Test 61 & 62 (Dec 8-10) ==<br />
* http://gangarobot.cern.ch/st/test_61/ <br />
* http://gangarobot.cern.ch/st/test_62/ <br />
300 jobs : IN2P3-LPC, GRIF-LPNHE, IN2P3-CPPM <br><br />
600 jobs : TOKYO <br><br />
Input DS Patterns: <br />
mc08.*Wmunu*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*Zprime_mumu*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*Zmumu*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*T1_McAtNlo*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*H*zz4l*.recon.AOD.e*_s*_r5*tid* <br />
mc08.*.recon.AOD.e*_s*_r5*tid*<br />
<br />
* Summary:<br />
- <b>TOKYO</b> reached the target : 15 evt/s - CPU/Walltime > 60 %<br />
only 3 jobs failure due to Athena crashes out of 600 jobs run<br />
Corrupted input AOD files found<br />
test 61, job 170, AOD.027097._37998.pool.root <br />
test 62, job 202, AOD.027579._24654.pool.root <br />
test 62, job 212, AOD.027076._10514.pool.root<br />
max. MySQL connections increased from 100, default, up to 200<br />
- <b>LPC</b>: 218 jobs (92.4 %) completed but not all input files could be read<br />
Number of input files processed by "completed" jobs ~29000 out of 58326 <br />
(expected to be)<br />
Site events/s less than 5 Hz - CPU/Walltime < 50 %<br />
Job 1.54, DS mc08.105001.pythia_minbias.recon.AOD.e357_s462_r541_tid027069): Expected 1000, Processed 4<br />
input files are available on disk <br />
rfio timeout seen in corresponding stderr<br />
rfio://clrgpfssrv03-dpm.in2p3.fr//storage/atlas1/atlas/2008-10-20/<br />
AOD.027069._03005.pool.root.1.2344130.0 can not be opened for reading<br />
(Timed out)<br />
<b>Possible work-around to be considered as applied in UK cloud</b> <br />
rfio tuning - increase of rfio bufsize on WNs <br />
See http://northgrid-tech.blogspot.com/2008/12/rfio-tuning-for-atlas-analysis-jobs.html<br />
- <b>CPPM</b>: <br />
Only 69 jobs sent because input datasets were unvalaible there<br />
27 failed jobs (no stdout, no stderr, did not even reach the CE) with<br />
the error message 'request expired' from WMS because of 'BrokerHelper:<br />
no compatible resources' (WMS log added to the monitoring page).<br />
This is seen sometimes by SAM ops test<br />
About 14 jobs remained in running state - seen running by site - doing<br />
nothing after 1 hour then killed by the batch scheduler<br />
no output/no logs = no clear disgnosis <br />
CPPM is using GRIF Topbdii. Impact of this ?<br />
<b>Decision taken to try to redistribute DS to Marseille to get more jobs <br />
but unsuccesfully </b><br />
- <b>GRIF-LPNHE</b> 1/3 of jobs remained in running state - seen then<br />
killed by the batch scheduler - no outputs/no logs = no clear disgnosis<br />
<br />
== Test 43 (November 28) ==<br />
* http://gangarobot.cern.ch/st/test_43/ 200 jobs over 12 sites<br />
* Problems seen : <br />
- Missing ATLAS release 14.2.20 @ CPPM <br />
<span style="color:green;">02/12/08 [DONE] validate-prod of 14.2.20 at marce01.in2p3.fr (IN2P3-CPPM)</span><br />
- Mapping CE-SE@GRIF-LAL and GRIF-SACLAY : Publication of multiple CloseSEs<br />
by LAL and IRFU cf https://savannah.cern.ch/bugs/index.php?44824<br />
<span style="color:green;">should be SOLVED by Ganga team</span><br />
- LFC bulk reading...End of LFC bulk reading...ERROR: Dataset(s)...is/are<br />
empty at GRIF-SACLAY_MCDISK / LAL_MCDISK <br />
(could be related to same problem)<br />
- ERROR@RO7-NIPNE : failed jobs with Athena errors <br />
http://gangarobot.cern.ch/st/test_43/gangadir/workspace/gangarbt<br />
/LocalAMGA/11/1/output/stdout.gz<br />
Core dump reading AOD file <br />
error reading from file rfio:tbit00.nipne.ro//storage1/atlas/2008-11-12/<br />
AOD.026357._00299.pool.root.1.810634.0 (Timed out)<br />
<span style="color:orange;">to be TRACKED</span> <br />
- NON FATAL ERRORS (completed jobs) @RO7-NIPNE, RO2-NIPNE : related to<br />
ATLASUSERDISK space token configuration<br />
ERROR during execution of lcg-cr --vo atlas -s ATLASUSERDISK<br />
ERROR: file not saved to RO-07-NIPNE_USERDISK in attempt number 3 ...<br />
ERROR: file not saved to RO-07-NIPNE_USERDISK - using now IN2P3-CC_USERDISK<br />
<span style="color:green;">CORRECTED</span></div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2882Atlas:BQSmonitoring2007-04-16T08:18:50Z<p>Lancone: /* Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] */</p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC ===<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
* ATLAS fraction at CC : ATLAS running jobs (green), ALL running jobs (blue), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_cc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_cc-day.png<br />
* LHC running (green) & waiting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all&farm=anastasie Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all&farm=anastasie Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Draft_of_the_scientific_programm&diff=2823Draft of the scientific programm2007-03-02T11:01:13Z<p>Lancone: /* <span style="color:#FF0000;">Les centres d’analyses */</p>
<hr />
<div>D.ation modèles de cP. 31/01/2007<br />
==== Objectifs ====<br />
LCG-France organise son 2ème colloque à Clermont-Ferrand les 14 et 15 mars 2007. Ces journées sont destinées à tous les acteurs de la grille de calcul au LHC (gestionnaires de site et utilisateurs) de l'IN2P3 et du Dapnia. Elles ont pour objectifs d’offrir un lieu d’échange et de communication sur les actions, les idées et les expériences en cours dans la mise en place du calcul pour le LHC dans le cadre du projet LCG.<br />
<br />
<br />
''' Programme Scientifique version 2 (9/2/07)'''<br />
<br />
<span style="color:#0000F0;"> 14 mars matin (3h30) 9h-10h45 11H15-13h pause 10h45-11h15<br />
<br />
==== <span style="color:#FF0000;"> 9h-9h05 Welcome ====<br />
<br />
==== <span style="color:#FF0000;"> Etat des lieux pour le calcul au LHC en France====<br />
<br />
''<span style="color:#006600;">Coordination : Ghita Rahal,CC-IN2P3; Dominique Pallin, LPC-Clermont ''<br />
<br />
* 09:05-09:15 -Infrastructure globale de grille en France et ressources associées F Malek<br />
* 09:20-09:50 -mise en place de La grille francaise : T1 F Hernandez<br />
* 09:55-10:20 -mise en place de La grille francaise: T2 etT3 F Chollet <br />
<br />
* 10:25-10:45 & 11h15-13:00 -Présentation de l'état du calcul dans les expériences:<br />
*** Les modèles de calcul des expériences (overview)<br />
*** Quelle participation dans la mise en place du calcul (en france)?<br />
*** Adéquation entre les infrastructures/ressources et les besoins.<br />
*** Etat de la production des données de simulation<br />
*** Etat d'avancement par rapport à l'objectif de la prise de données de fin 2007. <br />
*** Difficultés, les points à améliorer…<br />
*<br />
* 10:25-11:45 -ALICE Y schutz<br />
* 10:45-11h15 ----------------- Pause ---------------------------<br />
* 11:15-11:35 -ATLAS E Lancon <br />
* 11:40-12:00 -CMS C Charlot <br />
* 12:05-12:25 -LHCb A Tsaregorodtsev <br />
* 12:30-13:00 -discussion/tour de table sur l'ensemble de la session<br />
*** la grille francaise, sa mise en place et son utilisation, Du point de vue des sites, des collaborations LHC et des utilisateurs<br />
<br />
* <br />
<br />
<br />
<br />
<span style="color:#0000F0;"> 14 mars après-midi (3h) 14h45-16h15 16H45-18h15 pause 16h15-16h45<br />
<br />
==== <span style="color:#FF0000;"> Gestion et exploitation des grilles de calcul ==== <br />
<span style="color:#990000;">Couvrir 2 aspects complémentaires : <br />
<br />
<span style="color:#990000;">-les actions des sites -> les conséquences au niveau des utilisateurs<br />
<br />
<span style="color:#990000;">-les actions des utilisateurs -> les conséquences au niveau des sites <br />
<br />
<span style="color:#006600;">Coordination : Christine Leroy, Dapnia-Saclay; Pierre Girard, Ingénieur, CC-IN2P3<br />
<br />
* le fonctionnement d'un site de la grille :<br />
du déploiement du middleware à la gestion de sa production, en passant par les procédures qu'il doit suivre, comme la déclaration de "scheduled downtime", l'utilisation des outils officiels de monitoring (SAM, GSTAT, etc) et leurs conséquences (disparition partielle ou complète de la production, etc), sécurité,etc.<br />
<br />
* la gestion de jobs grilles : <br />
de la façon dont ils sont soumis par les utilisateurs à la façon dont ils sont traités par les sites (dont la mise au point des formules de rank pour l'élection d'un site de soumission, le manque d'attractivité d'un site pour les jobs ou l'inverse, la gestion des priorités sur les jobs, des jobs pilotes, exécuteurs, etc.)<br />
<br />
<br />
<B>A- Sous-session "Gestion des jobs grille"</B><br />
<br />
Dans cette première sous-session, il est demandé à chaque VO d'apporter des clarifications concernant les points suivants :<br />
<P><br />
<OL><br />
<LI>Méthode(s) de distribution des jobs sur les sites :<br />
<UL><br />
<LI>utilisation ou non d'un RB ?</LI><br />
<LI>utilisation ou non des informations publiées ?</LI><br />
<LI>Critère d'élection d'un site ? etc.</LI><br />
</UL><br />
</LI><br />
<LI>Organisation de la production<br />
<UL><br />
<LI>qui fait quoi, qui soumet quoi, les rôles, les histoires de priorité...</LI><br />
<LI>une production française ou pas</LI><br />
<LI>Système de monitoring pour les jobs ? Si oui, utilisable ou pas par les sites ? Quel est son principe de fonctionnement, etc.</LI><br />
<LI>gestion des proxy</LI><br />
<LI>Méthode d'installation des softs (+ desinstallation)</LI><br />
<LI>comment un nouvel OS est validé et l'information transmise</LI><br />
<br />
</UL><br />
</LI><br />
<LI>Amélioration attendue et perspectives pour la gestion des jobs</LI><br />
</OL><br />
</P><br />
<br />
14:45 Introduction (5', Christine/Pierre)<br />
14:50 Spécificités d'Alice (10', Artem ?)<br />
15:00 Spécificités d'Atlas (10', Jérôme Schwi? Stéphane ? Karim ?)<br />
15:10 Spécificités de Cms (10', Claude ? Artem ?)<br />
15:20 Spécificités de Lhcb (10', Andrei ou Sabine?)<br />
15:30 Discussions (45')<br />
<br />
<br />
<B>B- Sous-Session "Fonctionnement des sites" </B><br />
<br />
<P><br />
<B>16:45 "Exploitation globale de la grille" (20' + 10', Hélène C.)</B><br />
<UL><br />
<LI>Interaction entre outils de gestion de l'exploitation et la production</LI><br />
<LI>Comment les utilisateurs peuvent accéder aux informations</LI><br />
<LI>les outils d'exploitation (GOC DB, SAM, GSTAT, MonALISA et le CIC Portal)</LI><br />
<LI>L'accounting</LI> <br />
<LI>Comment mesurer l’efficacite d’un site (utilisationCPU/CPU; resource disponible/resource indisponible ;jobs plantes/ jobs/reussis)</LI><br />
</UL><br />
</P><br />
<br />
<P> <br />
<B>17:15 "Fonctionnement d’un site"? (45', 3 intervenants ?)</B><br />
<OL><br />
<LI>Suivi de jobs(15', David Bouvet)<br />
<UL><br />
<LI>Est-ce qu'on peut retracer un job qui a planté pour savoir ce qu'il a utilisé comme ressources et pourquoi il a planté?</LI><br />
<LI>Est-ce qu'on peut s'assurer qu'un job qui a bien tourné, a tourné avec les bonnes librairies (Y'a-t-il des vérifications par les sites?)</LI><br />
<LI>Detection de jobs qui se plantent instantanement car probleme sur un WN ?</LI><br />
</UL><br />
</LI><br />
<br />
<LI>Gestion des pannes(15',?)<br />
<UL><br />
<LI>Monitoring local, avez-vous un moyen de verifier « l’integrite » des WN ? Place disque disponible sur chaque WN</LI><br />
</UL><br />
</LI><br />
<br />
<LI>Le scheduling et le tuning (15', Michel Jouvin)<br />
<UL><br />
<LI>Peut on mixer job d’analyse et job de simulation sur les WNs (pour optimiser IO et CPU) ?</LI><br />
<LI>Le manque d'attractivité d'un site pour les jobs ou l'inverse => état des lieux et amélioration en vue côté mw if any</LI><br />
<LI>la gestion des priorités sur les jobs</LI><br />
</UL><br />
</LI><br />
</OL><br />
</P><br />
<br />
<P><br />
<B>17:45 "Gestion de l'infrastructure d'un site" (30',Pierre-Louis, Clermont)</B><br />
</P><br />
<br />
==== <span style="color:#FF0000;"> Mise en place d’un site ====<br />
<span style="color:#990000;">L’exemple du T2 du LPC Clermont-Ferrand. Visite du site possible durant les 2 jours par petits groupes<br />
<br />
* Salle machine (réseau électrique, climatisation,…)<br />
* Choix matériel<br />
* Sécurité<br />
* Les difficultés rencontrées<br />
<br />
<br />
<br />
<span style="color:#0000F0;"> 15 mars matin (3h30) 9h-10h45 11H15-13h pause 10h45-11h15<br />
<br />
==== <span style="color:#FF0000;"> Gestion des données grilles ====<br />
<span style="color:#990000;">Du point de vue des sites, des collaborations LHC et des utilisateurs<br />
<br />
''<span style="color:#006600;">Coordination : Lionel Schwarz (CC), Stéphane Jézequel(LAPP, Atlas) ''<br />
<br />
* Transferts massifs de données<br />
Dans cette partie, l'objectif est de comprendre l'utilisation de FTS et<br />
les outils de mouvement de fichiers (Phedex, DDM...) ce qui fonctionne,<br />
ce qui ne fonctionne pas. Il serait bon de rappeler le trajet des différentes<br />
donnees et lesquelles sont sous la responsabilite de quel site.<br />
Egalement, l'organisation en T2-T3, nuages... des donnees des<br />
expériences. Il faudrait obtenir des chiffres au niveau des debits<br />
prevus entre T1-T2.<br />
** Point sur l'infrastructure réseau et logicielle (FTS, SRM) des sites (5') - L. Schwarz<br />
** Transferts massifs Alice (10')<br />
** Transferts massifs Atlas (10')<br />
** Transferts massifs CMS (10')<br />
** Transferts massifs LHCb (10')<br />
** Discussion (15')<br />
<br />
* Accès aux données<br />
Cette partie est consacrée à la problématique de l'accès aux données par<br />
les jobs. Quel protocole est envisagé? Accès local/à distance?<br />
Debit prévu, nombre de jobs? Problème des données utilisateur? Cohabitation<br />
transfert des données/accès pour l'analyse. Téléchargement de données...<br />
** Modèle d'accès aux données de LHCb (10')<br />
** Modèle d'accès aux données de CMS (10')<br />
** Modèle d'accès aux données de Atlas (10')<br />
** Modèle d'accès aux données de Alice (10')<br />
** Discussion (30')<br />
<br />
<br />
<br />
<span style="color:#0000F0;"> 15 mars après-midi (2h40) 14h15-15h45 16H05-17h15 pause 15h45-16h05<br />
<br />
==== <span style="color:#FF0000;">Les centres d’analyses ==== <br />
<span style="color:#990000;">Quels sont les outils d'analyse? L'analyse sera t elle distribuee sur la grille ou centralisee dans des fermes dediees? Quels logiciels utiliser? Comment se situent les Tier2 et Tier3 ?<br />
<br />
''<span style="color:#006600;">Coordination : Eric Lancon,Dapnia-Saclay ; Claude Charlot LLR; Frédéric Derue LPNHE ''<br />
<br />
* mise en place<br />
* les contours<br />
* les logiciels d’analyses (Ganga,..)<br />
* Coordination avec les T3s ? mise en commun de ressources ?<br />
<br />
==== <span style="color:#FF0000;"> Conclusions F Malek ====<br />
<br />
*</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2684Atlas:BQSmonitoring2007-01-17T20:52:40Z<p>Lancone: /* ATLAS & LHC at CC */</p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC ===<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
* ATLAS fraction at CC : ATLAS running jobs (green), ALL running jobs (blue), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_cc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_cc-day.png<br />
* LHC running (green) & waiting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2683Atlas:BQSmonitoring2007-01-17T20:50:28Z<p>Lancone: /* ATLAS & LHC at CC */</p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC ===<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
* ATLAS fraction at CC : ATLAS running jobs (green), ALL running jobs (blue), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_cc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_cc-day.png<br />
* LHC running (green) & waiting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2626Atlas:BQSmonitoring2006-12-07T15:37:00Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC ===<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
* LHC running (green) & waiting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2625Atlas:BQSmonitoring2006-12-07T15:32:54Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC ===<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2624Atlas:BQSmonitoring2006-12-07T15:25:57Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC ===<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2623Atlas:BQSmonitoring2006-12-07T15:25:15Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== ATLAS & LHC at CC<br />
* ATLAS & LHC at CC : LHC (blue), ATLAS (green), ATLAS fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas_lhc-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2622Atlas:BQSmonitoring2006-12-07T15:11:47Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2621Atlas:BQSmonitoring2006-12-07T14:13:31Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Production [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio.html more] ===<br />
* Production Jobs : running (green), queued (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2483Atlas:BQSmonitoring2006-11-22T09:22:12Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Production ===<br />
* Production Jobs : running (green), queued (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlasprod-day.png<br />
* Production jobs (green), all grid jobs (blue), fraction (orange)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/prod_all_ratio-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2476Atlas:BQSmonitoring2006-11-17T13:48:30Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS Jobs : running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
*ATLAS GRID jobs : running (green), waiting (blue)<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_grid_atlas-day.png<br />
* ATLAS RUNNING jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2445Atlas:BQSmonitoring2006-11-06T10:28:16Z<p>Lancone: </p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
* ATLAS grid jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas&diff=2444Atlas2006-11-06T10:25:54Z<p>Lancone: </p>
<hr />
<div>== ''Bienvenue sur la page Atlas LCG-France <br><br> Welcome to the LCG-France Atlas page'' ==<br />
<br />
*Experiment computing Representative : Eric Lancon <br />
*Sites : CPPM, LAL, LAPP, LPNHE, LPC Clermont Fd, SACLAY<br />
*Associated sites : BEIJING, TOKYO, NIPNE<br />
*Web site : http://atlas.web.cern.ch/Atlas/index.html<br />
<br />
=== SC4 Atlas ===<br />
* Dataset Transfer Exercise [[Atlas:SC4|T0->T1->T2]] (19 June-End July)<br />
* Dataset Transfer Exercise [[Atlas:SC4-Sept06|T0->T1->T2]] (25 September-18 October)<br />
* [[ Atlas:SC4-repro| Data reprocessing in T1s]] exercise<br />
* [[ Atlas:SC4-analyse| Distributed analysis]]<br />
<br />
=== Fonctionnal tests ===<br />
* [https://uimon.cern.ch/twiki/bin/view/Atlas/DDMOperations#Data_transfer_Functional_test_Ti Central information]<br />
* 11-15 September 2006 : Dataset Transfer Exercise : Detailed information for [[ Atlas:Functionnal-test-lyon| LYONregion ]]<br />
* 20 October for 7-10 days : Dataset Transfer Exercise : Detailed information for [[Atlas:Functionnal-test-lyon-oct06| LYONregion ]]<br />
* Week 47-48 <br />
*January 2007 (Maybe performance test)<br />
<br />
=== MC Production and data replication ===<br />
* [[Atlas:cloudFR | Informations]] about MC production in the FR cloud<br />
* [http://atlas-php.web.cern.ch/atlas-php/DbAdmin/Ora/php-4.3.4/proddb/monitor/Home.php MC Production monitoring]<br />
* Dataset replication [[Atlas:csc11-replication | csc11]]<br />
<br />
=== Distributed analysis ===<br />
* [[Atlas:sites | Sites description]] : queues, SE, ...<br />
<br />
=== Resources monitoring ===<br />
* [[ Atlas:DDMmonitoring| DDM monitoring ]]<br />
* Monitoring of LYON site<br />
**[http://cctools.in2p3.fr/dcache/transfers/atlas-sc4.html Monitoring of dcache access (read/write) for SC4 areas]<br />
**[http://cctools.in2p3.fr/dcache/transfers/plots.php?vo=atlas Monitoring of dcache access by T2 sites in the last 24 hours]<br />
** [http://ccsmurf.in2p3.fr:8080/perl/graph-db.pl?hostname=cclcglfcli04&start=now-7days&end=now-15min&step=60&multihost= LFC server in Lyon monitoring] (includes all LHC VOs) (''only visible from in2p3 domain'')<br />
** [http://ccsmurf.in2p3.fr:8080/perl/graph-db.pl?hostname=cclcgftsli02&start=now-7days&end=now-15min&step=60&multihost= FTS server in Lyon monitoring] (serve all LHC VOs) (''only visible from in2p3 domain'')<br />
** [http://atlas-france.in2p3.fr/Activites/Informatique/OutilsCC/VO-cclcgatlas VOBOX monitoring]<br />
** [[Atlas:BQSmonitoring| BQS monitoring]]<br />
* General monitoring<br />
** [http://gridview.cern.ch/GRIDVIEW/index.php FTS monitoring] from Gridview<br />
** [http://gridview.cern.ch/GRIDVIEW/same_index.php Site availability] from Gridview<br />
** [https://lcg-sam.cern.ch:8443/sam/sam.py SAM]<br />
** [http://goc.grid-support.ac.uk/gridsite/operations/downtimes.php Schedulded downtime for sites]<br />
* FR cloud monitoring<br />
** [[Atlas:cloudFR#Site_CPU_monitoring | Sites CPU monitoring]]<br />
** [[Atlas:cloudFR#Site_disk_monitoring | Available disk space]] (Using command ''lcg-info --list-se --query "SE=xxxx" --vo atlas --attrs 'AvailableSpace' '')<br />
* Tools</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas&diff=2443Atlas2006-11-06T10:24:43Z<p>Lancone: /* Resources monitoring */</p>
<hr />
<div>== ''Bienvenue sur la page Atlas LCG-France <br><br> Welcome to the LCG-France Atlas page'' ==<br />
<br />
*Experiment computing Representative : Eric Lancon <br />
*Sites : CPPM, LAL, LAPP, LPNHE, LPC Clermont Fd, SACLAY<br />
*Associated sites : BEIJING, TOKYO, NIPNE<br />
*Web site : http://atlas.web.cern.ch/Atlas/index.html<br />
<br />
=== SC4 Atlas ===<br />
* Dataset Transfer Exercise [[Atlas:SC4|T0->T1->T2]] (19 June-End July)<br />
* Dataset Transfer Exercise [[Atlas:SC4-Sept06|T0->T1->T2]] (25 September-18 October)<br />
* [[ Atlas:SC4-repro| Data reprocessing in T1s]] exercise<br />
* [[ Atlas:SC4-analyse| Distributed analysis]]<br />
<br />
=== Fonctionnal tests ===<br />
* [https://uimon.cern.ch/twiki/bin/view/Atlas/DDMOperations#Data_transfer_Functional_test_Ti Central information]<br />
* 11-15 September 2006 : Dataset Transfer Exercise : Detailed information for [[ Atlas:Functionnal-test-lyon| LYONregion ]]<br />
* 20 October for 7-10 days : Dataset Transfer Exercise : Detailed information for [[Atlas:Functionnal-test-lyon-oct06| LYONregion ]]<br />
* Week 47-48 <br />
*January 2007 (Maybe performance test)<br />
<br />
=== MC Production and data replication ===<br />
* [[Atlas:cloudFR | Informations]] about MC production in the FR cloud<br />
* [http://atlas-php.web.cern.ch/atlas-php/DbAdmin/Ora/php-4.3.4/proddb/monitor/Home.php MC Production monitoring]<br />
* Dataset replication [[Atlas:csc11-replication | csc11]]<br />
<br />
=== Distributed analysis ===<br />
* [[Atlas:sites | Sites description]] : queues, SE, ...<br />
<br />
=== Resources monitoring ===<br />
* [[ Atlas:DDMmonitoring| DDM monitoring ]]<br />
* Monitoring of LYON site<br />
**[http://cctools.in2p3.fr/dcache/transfers/atlas-sc4.html Monitoring of dcache access (read/write) for SC4 areas]<br />
**[http://cctools.in2p3.fr/dcache/transfers/plots.php?vo=atlas Monitoring of dcache access by T2 sites in the last 24 hours]<br />
** [http://ccsmurf.in2p3.fr:8080/perl/graph-db.pl?hostname=cclcglfcli04&start=now-7days&end=now-15min&step=60&multihost= LFC server in Lyon monitoring] (includes all LHC VOs) (''only visible from in2p3 domain'')<br />
** [http://ccsmurf.in2p3.fr:8080/perl/graph-db.pl?hostname=cclcgftsli02&start=now-7days&end=now-15min&step=60&multihost= FTS server in Lyon monitoring] (serve all LHC VOs) (''only visible from in2p3 domain'')<br />
** [http://atlas-france.in2p3.fr/Activites/Informatique/OutilsCC/VO-cclcgatlas VOBOX monitoring]<br />
** [Atlas:BQSmonitoring, BQS monitoring]<br />
* General monitoring<br />
** [http://gridview.cern.ch/GRIDVIEW/index.php FTS monitoring] from Gridview<br />
** [http://gridview.cern.ch/GRIDVIEW/same_index.php Site availability] from Gridview<br />
** [https://lcg-sam.cern.ch:8443/sam/sam.py SAM]<br />
** [http://goc.grid-support.ac.uk/gridsite/operations/downtimes.php Schedulded downtime for sites]<br />
* FR cloud monitoring<br />
** [[Atlas:cloudFR#Site_CPU_monitoring | Sites CPU monitoring]]<br />
** [[Atlas:cloudFR#Site_disk_monitoring | Available disk space]] (Using command ''lcg-info --list-se --query "SE=xxxx" --vo atlas --attrs 'AvailableSpace' '')<br />
* Tools</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:BQSmonitoring&diff=2442Atlas:BQSmonitoring2006-11-06T10:22:54Z<p>Lancone: BQS USAGE</p>
<hr />
<div>== "ATLAS BQS USAGE MONITORING" <br> ==<br />
<br />
=== BQS global vue [http://cctools.in2p3.fr/mrtguser/compta_bqs.php more] ===<br />
*ATLAS running (green) and wainting (blue) jobs [http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs.html more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/atlas/atlas_jobs-day.png<br />
* ATLAS grid jobs : all jobs (blue), grid (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/info_lcg_helene.php more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_atlas-day.png<br />
* LHC on BQS : all jobs (blue), LHC (green), fraction (orange) [http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all.htm more]<br />
http://cctools.in2p3.fr/mrtguser/mrtguser/ccin2p3/lcg_helene_lhc_all-day.png<br />
<br />
=== Statistiques [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.html more] ===<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=day&type=group&platform=all, Daily CPU consumption]<br />
* [http://cctools.in2p3.fr/mrtguser/compta_bqs/compta_bqs.php?var=week&type=group&platform=all, Weekly consumption ]</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:cloudFR&diff=2405Atlas:cloudFR2006-10-23T15:30:30Z<p>Lancone: </p>
<hr />
<div>== Potential available ressources (CPU) for simulation phase==<br />
* Refer to Simone's [http://grid-deployment.web.cern.ch/grid-deployment/cgi-bin/ATLAS-qstat page]<br />
* LYON : ~400 <br />
* LPC : 190<br />
* CPPM : 14<br />
* LAL : 132<br />
* SACLAY: 206<br />
* LPNHE: 20<br />
* TOKYO : 80<br />
* BEIJING : 28<br />
* NIPNE : 98<br />
* LAPP : 2 <br />
<br />
* LLR : 52 <br />
== News ==<br />
* Production 12.0.3<br />
<br />
== Tools ==<br />
* Jobs running in the FR cloud : '' lcg-info --list-ce --vo atlas --query 'Tag=VO-atlas-cloud-FR' --attrs 'RunningJobs,WaitingJobs' ''<br />
* CPU declared in the FR cloud : '' lcg-info --list-ce --vo atlas --query 'Tag=VO-atlas-cloud-FR' --attrs 'TotalCPUs' ''<br />
<br />
== Problems ==<br />
* 30 September <br />
** HITS files are transfered by DDM to LYONDISK instead of LYONTAPE -- Solution : New version of [https://uimon.cern.ch/twiki/bin/view/Atlas/DDMProdSysClient#Usage subscribeToTier1], code provided by DDM team for prodsys<br />
** dcache directory /pnfs/in2p3.fr/data/atlas/disk/dq2/misal1_csc11 belongs to root <br />
Solution : Needs intervention of dcache administrator (1 October : Solved)<br />
<br />
== Site CPU monitoring ==<br />
=== LYON [http://goc.grid.sinica.edu.tw/gstat/IN2P3-CC/cclcgceli02atla_job_.html more] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-CC/cclcgceli02atla_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-CC/GIISQuery_Usage_cpu_week.png <br />
=== MARSEILLE [http://goc.grid.sinica.edu.tw/gstat/IN2P3-CPPM/marseillece01at_job_.html more] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-CPPM/marseillece01at_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-CPPM/GIISQuery_Usage_cpu_week.png <br />
=== ANNECY [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LAPP/lappce01atlas_job_.html more] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LAPP/lappce01atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-LAPP/GIISQuery_Usage_cpu_week.png<br />
<br />
=== CLERMONT-FERRAND [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce01atlas_job_.html CE01] [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce02atlas_job_.html CE02] [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce03atlas_job_.html CE03] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce01atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/GIISQuery_Usage_cpu_day.png <br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce02atlas_job_week.png <br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce03atlas_job_week.png<br />
<br />
=== GRIF [http://goc.grid.sinica.edu.tw/gstat/GRIF/grid10atlas_job_.html LAL] [http://goc.grid.sinica.edu.tw/gstat/GRIF/node07atlas_job_.html SACLAY] [http://goc.grid.sinica.edu.tw/gstat/GRIF/lpnceatlas_job_.html LPNHE] [http://goc.grid.sinica.edu.tw/gstat/GRIF/polgrid1atlas_job_.html LLR] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/grid10atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/GRIF/GIISQuery_Usage_cpu_day.png <br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/lpnceatlas_job_week.png <br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/node07atlas_job_week.png <br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/polgrid1atlas_job_week.png<br />
<br />
=== BEIJING [http://goc.grid.sinica.edu.tw/gstat/BEIJING-LCG2/lcg002atlas_job_.html more]===<br />
* http://goc.grid.sinica.edu.tw/gstat/BEIJING-LCG2/lcg002atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/BEIJING-LCG2/GIISQuery_Usage_cpu_week.png<br />
<br />
=== TOKYO [http://goc.grid.sinica.edu.tw/gstat/TOKYO-LCG2/dgce0atlas_job_.html more]===<br />
* http://goc.grid.sinica.edu.tw/gstat/TOKYO-LCG2/dgce0atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/TOKYO-LCG2/GIISQuery_Usage_cpu_week.png<br />
<br />
=== NIPNE [http://goc.grid.sinica.edu.tw/gstat/RO-02-NIPNE/tbat01atlas_job_.html more]===<br />
* http://goc.grid.sinica.edu.tw/gstat/RO-02-NIPNE/tbat01atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/RO-02-NIPNE/GIISQuery_Usage_cpu_week.png</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas:cloudFR&diff=2390Atlas:cloudFR2006-10-19T07:19:52Z<p>Lancone: </p>
<hr />
<div>== Potential available ressources (CPU) for simulation phase==<br />
* Refer to Simone's [http://grid-deployment.web.cern.ch/grid-deployment/cgi-bin/ATLAS-qstat page]<br />
* LYON : ~400 <br />
* LPC : 190<br />
* CPPM : 14<br />
* LAL : 132<br />
* SACLAY: 206<br />
* LPNHE: 20<br />
* TOKYO : 80<br />
* BEIJING : 28<br />
* NIPNE : 98<br />
* LAPP : 2 <br />
<br />
* LLR : 52 <br />
== News ==<br />
* Production 12.0.3<br />
<br />
== Tools ==<br />
* Jobs running in the FR cloud : '' lcg-info --list-ce --vo atlas --query 'Tag=VO-atlas-cloud-FR' --attrs 'RunningJobs,WaitingJobs' ''<br />
* CPU declared in the FR cloud : '' lcg-info --list-ce --vo atlas --query 'Tag=VO-atlas-cloud-FR' --attrs 'TotalCPUs' ''<br />
<br />
== Problems ==<br />
* 30 September <br />
** HITS files are transfered by DDM to LYONDISK instead of LYONTAPE -- Solution : New version of [https://uimon.cern.ch/twiki/bin/view/Atlas/DDMProdSysClient#Usage subscribeToTier1], code provided by DDM team for prodsys<br />
** dcache directory /pnfs/in2p3.fr/data/atlas/disk/dq2/misal1_csc11 belongs to root <br />
Solution : Needs intervention of dcache administrator (1 October : Solved)<br />
<br />
== Site CPU monitoring ==<br />
=== LYON [http://goc.grid.sinica.edu.tw/gstat/IN2P3-CC/cclcgceli02atla_job_.html more] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-CC/cclcgceli02atla_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-CC/GIISQuery_Usage_cpu_week.png <br />
=== MARSEILLE [http://goc.grid.sinica.edu.tw/gstat/IN2P3-CPPM/marseillece01at_job_.html more] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-CPPM/marseillece01at_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-CPPM/GIISQuery_Usage_cpu_week.png <br />
=== ANNECY [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LAPP/lappce01atlas_job_.html more] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LAPP/lappce01atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-LAPP/GIISQuery_Usage_cpu_week.png<br />
<br />
=== CLERMONT-FERRAND [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce01atlas_job_.html CE01] [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce02atlas_job_.html CE02] [http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce03atlas_job_.html CE03] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce01atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/GIISQuery_Usage_cpu_day.png <br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce02atlas_job_week.png <br />
* http://goc.grid.sinica.edu.tw/gstat/IN2P3-LPC/clrlcgce03atlas_job_week.png<br />
<br />
=== GRIF [http://goc.grid.sinica.edu.tw/gstat/GRIF/grid10atlas_job_.html LAL] [http://goc.grid.sinica.edu.tw/gstat/GRIF/node07atlas_job_.html SACLAY] [http://goc.grid.sinica.edu.tw/gstat/GRIF/lpnceatlas_job_.html LPNHE] [http://goc.grid.sinica.edu.tw/gstat/GRIF/polgrid1atlas_job_.html LLR] ===<br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/grid10atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/GRIF/GIISQuery_Usage_cpu_day.png <br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/lpnceatlas_job_week.png <br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/node07atlas_job_week.png <br />
* http://goc.grid.sinica.edu.tw/gstat/GRIF/polgrid1atlas_job_week.png<br />
<br />
=== BEIJING [http://goc.grid.sinica.edu.tw/gstat/BEIJING-LCG2/lcg002atlas_job_.html more]===<br />
* http://goc.grid.sinica.edu.tw/gstat/BEIJING-LCG2/lcg002atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/BEIJING-LCG2/GIISQuery_Usage_cpu_week.png<br />
<br />
=== TOKYO [http://goc.grid.sinica.edu.tw/gstat/TOKYO-LCG2/dgce0atlas_job_.html more]===<br />
* http://goc.grid.sinica.edu.tw/gstat/TOKYO-LCG2/dgce0atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/TOKYO-LCG2/GIISQuery_Usage_cpu_week.png<br />
<br />
=== NIPNE [http://goc.grid.sinica.edu.tw/gstat/RO-02-NIPNE/tbat01atlas_job_.html more]===<br />
* http://goc.grid.sinica.edu.tw/gstat/RO-02-NIPNE/tbat01atlas_job_week.png http://goc.grid.sinica.edu.tw/gstat/RO-02-NIPNE/GIISQuery_Usage_cpu_week.png</div>Lanconehttps://lcg.in2p3.fr/index.php?title=Atlas&diff=2318Atlas2006-10-11T07:56:02Z<p>Lancone: </p>
<hr />
<div>__NOTOC__<br />
== ''Bienvenue sur la page Atlas LCG-France <br><br> Welcome to the LCG-France Atlas page'' ==<br />
<br />
*Experiment computing Representative : Eric Lancon <br />
*Sites : CPPM, LAL, LAPP, LPNHE, LPC Clermont Fd, SACLAY<br />
*Associated sites : BEIJING, TOKYO, NIPNE<br />
*Web site : http://atlas.web.cern.ch/Atlas/index.html<br />
<br />
<br />
=== SC4 Atlas ===<br />
* Dataset Transfer Exercise [[Atlas:SC4|T0->T1->T2]] (19 June-End July)<br />
* Dataset Transfer Exercise [[Atlas:SC4-Sept06|T0->T1->T2]] (25 September for 3 weeks)<br />
* [[ Atlas:SC4-repro| Data reprocessing in T1s]] exercise<br />
* [[ Atlas:SC4-analyse| Distributed analysis]]<br />
<br />
=== Fonctionnal tests ===<br />
* [https://uimon.cern.ch/twiki/bin/view/Atlas/DDMOperations#Data_transfer_Functional_test_Ti Central information]<br />
* 11-15 September 2006 : Dataset Transfer Exercise : Detailed information for [[ Atlas:Functionnal-test-lyon| LYONregion ]]<br />
* 15 October for 7-10 days : Dataset Transfer Exercise : Detailed information for [[Atlas:Functionnal-test-lyon-oct06| LYONregion ]]<br />
* Week 47-48 <br />
*January 2007 (Maybe performance test)<br />
<br />
=== MC Production and data replication ===<br />
* [[Atlas:cloudFR | Informations]] about MC production in the FR cloud<br />
* [http://atlas-php.web.cern.ch/atlas-php/DbAdmin/Ora/php-4.3.4/proddb/monitor/Home.php MC Production monitoring]<br />
* Dataset replication [[Atlas:csc11-replication | csc11]]<br />
<br />
=== Distributed analysis ===<br />
* [[Atlas:sites | Sites description]] : queues, SE, ...<br />
<br />
=== Resources monitoring ===<br />
* [[ Atlas:DDMmonitoring| DDM monitoring ]]<br />
* Monitoring of LYON site<br />
**[http://cctools.in2p3.fr/dcache/transfers/atlas-sc4.html Monitoring of dcache access (read/write) for SC4 areas]<br />
**[http://cctools.in2p3.fr/dcache/transfers/plots.php?vo=atlas Monitoring of dcache access by T2 sites in the last 24 hours]<br />
** [http://ccsmurf.in2p3.fr:8080/perl/graph-db.pl?hostname=cclcglfcli04&start=now-7d&end=now-15min&step=60&multihost= LFC in Lyon monitoring] (includes all LHC VOs)<br />
** [http://atlas-france.in2p3.fr/Activites/Informatique/OutilsCC/VO-cclcgatlas VOBOX monitoring]<br />
* General monitoring<br />
** [http://gridview.cern.ch/GRIDVIEW/index.php FTS monitoring] from Gridview<br />
** [http://gridview.cern.ch/GRIDVIEW/same_index.php Site availability] from Gridview<br />
** [https://lcg-sam.cern.ch:8443/sam/sam.py SAM]<br />
* Tools<br />
** Check SE disk space availability for ATLAS: ''lcg-info --list-se --query "SE=*.fr" --vo atlas --attrs 'AvailableSpace' ''</div>Lancone