Atlas:CCRC08May

Un article de lcgwiki.
Revision as of 08:28, 30 mai 2008 by Ueda (talk | contribs) (Thu, 29 May)
Jump to: navigation, search

Monitoring pages/graphs

FTS

http://cctoolsafs.in2p3.fr/fts/monitoring/prod/ftsmonitor.php?vo=atlas

T0-T1 (ALL)

http://atldq2pro.cern.ch:8000/ft/mon/ftmon_tier1s.html

http://dashb-atlas-data-tier0.cern.ch/dashboard/request.py/site

  • Throughput
http://dashb-atlas-data-tier0.cern.ch/dashboard/templates/plots/OVERVIEW.throughput.14400.png
  • Errors
http://dashb-atlas-data-tier0.cern.ch/dashboard/templates/plots/OVERVIEW.num_file_xs_error.14400.png

T0-T1 (Lyon)

http://dashb-atlas-data-tier0.cern.ch/dashboard/request.py/site?statsInterval=4&name=LYON

  • Throughput T0-LYON
http://dashb-atlas-data-tier0.cern.ch/dashboard/templates/plots/LYON.throughput.14400.png
  • Errors T0-LYON
http://dashb-atlas-data-tier0.cern.ch/dashboard/templates/plots/LYON.num_file_xs_error.14400.png
  • Throughput Others-LYON
http://dashb-atlas-data.cern.ch/dashboard/templates/plots/LYON.T1.throughput.14400.png

T1-T1

http://atldq2pro.cern.ch:8000/ft/mon/ftmon_T1-T1.html

T1-T2 (Lyon)

http://atldq2pro.cern.ch:8000/ft/mon/ftmon_tier2s.html http://atldq2pro.cern.ch:8000/ft/mon/ftmon_T1-T2_matrix_day.html

http://dashb-atlas-data.cern.ch/dashboard/request.py/site?statsInterval=4&name=LYON

  • Throughput
http://dashb-atlas-data.cern.ch/dashboard/templates/plots/LYON.T2.throughput.14400.png
  • Errors
http://dashb-atlas-data.cern.ch/dashboard/templates/plots/LYON.T2.num_file_xs_error.14400.png

Network Graphs

IN2P3 Weathermap
cc-in2p3 
lyo-cern (lhcopn-in2p3.cern.ch)
http://netstat.in2p3.fr/weathermap/graphiques/lyo-cern-daily.gif
lyon-nord 
lyo-nrd
http://netstat.in2p3.fr/weathermap/graphiques/lyo-nrd-daily.gif
orsay 
orsay (in2p3-orsay.cssi.renater.fr
http://netstat.in2p3.fr/weathermap/graphiques/orsay-daily.gif
lal-cc 
Liaison LAL - CC
http://netstat.in2p3.fr/weathermap/graphiques/lal-cc-daily.gif
lal 
lal
http://netstat.in2p3.fr/weathermap/graphiques/lal-daily.gif
lpnhe
lpnhe-nrd (in2p3-jussieu.cssi.renater.fr)
http://netstat.in2p3.fr/weathermap/graphiques/lpnhe-nrd-daily.gif
lpnhe (Paris-LPNHE.in2p3.fr)
http://netstat.in2p3.fr/weathermap/graphiques/lpnhe-daily.gif
lapp 
ann-nrd
http://netstat.in2p3.fr/weathermap/graphiques/ann-nrd-daily.gif
lpc
lpc-cf

http://netstat.in2p3.fr/weathermap/graphiques/lpc-cf-daily.gif

lpsc 
lpsc
http://netstat.in2p3.fr/weathermap/graphiques/lpsc-daily.gif
cppm 
cppm

http://netstat.in2p3.fr/weathermap/graphiques/cppm-daily.gif

international (tokyo etc.) 
parisnrd

http://netstat.in2p3.fr/weathermap/graphiques/parisnrd-daily.gif

GEANT - NYC 
MANLAN

http://dc-snmp.wcc.grnoc.iu.edu/manlan/img/sw.newy32aoa.manlan.internet2.edu--te10_1-std5.gif

NYC - TOKYO 
MANLAN

http://dc-snmp.wcc.grnoc.iu.edu/manlan/img/sw.newy32aoa.manlan.internet2.edu--te11_1-std5.gif

tokyo 
gridftp monitor
http://www.icepp.jp/monitor/gridftp/img/all.png

T0-T1 transfer tests (week1)

T1-T1 transfer tests (week2)

Some summaries presented at ADC Operations Meeting http://indico.cern.ch/conferenceDisplay.py?confId=33976

T0-T1-T2 transfer tests (week3)

General remarks

https://twiki.cern.ch/twiki/bin/view/Atlas/DDMOperationsGroup#CCRC08_2_May_2008

The T0 load generator will run at "peak" rate for 3 days ("peak" rate means data from 24h/day of detector data taking at 200Hz are distributed in 24h, while "nominal" rate means data from 14 hours/day of detector data taking at 200Hz are distributed in 24h).

At peak rate 17,280,000 events/day are produced, corresponding to 27.6 TB/day of RAW, 17.3 TB/day of ESD and 3.5 TB/day of AOD (considering the sizes of 1.6 MB/event for RAW, 1.0 MB/event for ESD and 0.2 MB/event for AOD)

  • It turned out that AOD size was 0.1 MB/event; 1.7TB/day.
monitoring page

data replication from CERN to Tier-1s http://panda.atlascomp.org/?mode=listFunctionalTests

data replication within clouds http://panda.atlascomp.org/?mode=listFunctionalTests&testType=T1toT2s

Summaries / Reports

CCRC08 https://twiki.cern.ch/twiki/bin/viewfile/LCG/CCRC08DailyMeetingsWeek080519?rev=1;filename=ATLAS-TT-CCRC08-May22.ppt

ADC Oper 22 May http://indico.cern.ch/materialDisplay.py?contribId=3&materialId=slides&confId=34556

T0-T1(LYON)

Shipping continuously data to T1s according to computing model, sites should demonstrate to sustain for 3 days the following export rates

SITE TAPE DISK TOTAL
IN2P3 48.00 MB/s 100.00 MB/s 148.00 MB/s

Metric for success: Sites should be capable of sustaining 90% of the mentioned rates (for both disk and tape) for at least 2 days of test. For sites who would like to test higher throughput, we can oversubscribe (both to disk and tape).

As a reminder, here the table of the necessary space needed at each T1

SITE TAPE DISK
IN2P3 12.4416 TB 25.92 TB

replication status is checked ~ every 2h http://pandamon.usatlas.bnl.gov:25880/server/pandamon/query?mode=listFunctionalTests


T1-T2

T2s will receive AODs, which should be generated at a rate of 3.5TB/day 1.7TB/day. The amount that each site receives depends on the share as written in https://twiki.cern.ch/twiki/bin/view/Atlas/DDMOperationsGroup#CCRC08_2_May_2008

 IN2P3-LAPP_DATADISK:   12%      2.4MB/s  0.20TB/day  0.60TB/3d
 IN2P3-CPPM_DATADISK:    5%      1.0MB/s, 0.09TB/day, 0.27TB/3d
 IN2P3-LPSC_DATADISK:    5%      1.0MB/s, 0.09TB/day, 0.27TB/3d
 IN2P3-LPC_DATADISK:    13%      2.6MB/s, 0.22TB/day, 0.66TB/3d
 GRIF-LAL_DATADISK:     30%      6.0MB/s, 0.51TB/day, 1.53TB/3d
 GRIF-LPNHE_DATADISK:   15%      3.0MB/s, 0.26TB/day, 0.78TB/3d
 GRIF-SACLAY_DATADISK:  20%      4.0MB/s, 0.34TB/day, 1.02TB/3d
 BEIJING-LCG2_DATADISK: 20%      4.0MB/s, 0.34TB/day, 1.02TB/3d
 RO-07-NIPNE_DATADISK:  10%      2.0MB/s, 0.17TB/day, 0.51TB/3d
 RO-02-NIPNE_DATADISK:  10%      2.0MB/s, 0.17TB/day, 0.51TB/3d
 TOKYO-LCG2_DATADISK:   50%      10.MB/s, 0.85TB/day, 2.55TB/3d
 ---------------------------------------------------------------
 Total:                190%     37.5MB/s, 3.24TB/day, 9.72TB/3d

The shares are decided rather arbitrary according to the free space in ATLASDATADISK. These numers can be raised at a later stage of the test, but at first we would like to be sure everythinig goes well with this rate.

The shares were increased around 2008-05-24 00:00 (CET)

 IN2P3-LAPP_DATADISK :   25%     5.0MB/s, 0.43TB/day, 1.3TB/3d
 IN2P3-CPPM_DATADISK :    5%     1.0MB/s, 0.09TB/day, 0.3TB/3d
 IN2P3-LPSC_DATADISK :    5%     1.0MB/s, 0.09TB/day, 0.3TB/3d
 IN2P3-LPC_DATADISK :    25%     5.0MB/s, 0.43TB/day, 1.3TB/3d
 BEIJING-LCG2_DATADISK : 20%     4.0MB/s, 0.35TB/day, 1.0TB/3d
 RO-07-NIPNE_DATADISK :  10%     2.0MB/s, 0.17TB/day, 0.5TB/3d
 RO-02-NIPNE_DATADISK :  10%     2.0MB/s, 0.17TB/day, 0.5TB/3d
 GRIF-LAL_DATADISK :     45%     9.0MB/s, 0.77TB/day, 2.3TB/3d
 GRIF-LPNHE_DATADISK :   25%     5.0MB/s, 0.43TB/day, 1.3TB/3d
 GRIF-SACLAY_DATADISK :  30%     6.0MB/s, 0.52TB/day, 1.6TB/3d
 TOKYO-LCG2_DATADISK :  100%    20.0MB/s, 1.73TB/day, 5.2TB/3d
 ------------------------------------------------------------------
 Total :                300%    60.0MB/s, 5.18TB/day, 15.6TB/3d


Datasets are subscribed from parent Tier-1s ~ every 4h

replication status is checked ~ every 2h http://pandamon.usatlas.bnl.gov:25880/server/pandamon/query?mode=listFunctionalTests&testType=T1toT2s

Lyon FTS monitor: http://cctoolsafs.in2p3.fr/fts/monitoring/prod/ftsmonitor.php?vo=atlas

Contacts:

  • IN2P3-CPPM_DATADISK :
  • IN2P3-LPSC_DATADISK :
  • IN2P3-LPC_DATADISK :
  • GRIF-LAL_DATADISK : (grid.admin a lal.in2p3.fr)
  • GRIF-LPNHE_DATADISK :
  • GRIF-SACLAY_DATADISK :
  • BEIJING-LCG2_DATADISK : (yanxf a ihep.ac.cn, Erming.Pei a cern.ch)
  • RO-07-NIPNE_DATADISK : (ciubancan a nipne.ro)
  • RO-02-NIPNE_DATADISK : (tpreda a nipne.ro)
  • TOKYO-LCG2_DATADISK : (lcg-admin a icepp.s.u-tokyo.ac.jp)


Summary

Short visio conf to summarize what were done this week, and what to prepare for the next week http://indico.in2p3.fr/conferenceDisplay.py?confId=914

Statistics from dq2 commands
site datasets files TB
BEIJING-LCG2_DATADISK 102 159 0.5724
GRIF-LAL_DATADISK 231 310 1.116
GRIF-LPNHE_DATADISK 136 213 0.7668
GRIF-SACLAY_DATADISK 144 248 0.8928
IN2P3-CPPM_DATADISK 23 39 0.1404
IN2P3-LAPP_DATADISK 129 217 0.7812
IN2P3-LPC_DATADISK 136 213 0.7668
IN2P3-LPSC_DATADISK 23 25 0.09
RO-02-NIPNE_DATADISK 39 69 0.2484
RO-07-NIPNE_DATADISK 52 99 0.3564
TOKYO-LCG2_DATADISK 626 974 3.5064


                                                  dq2          srm free TB 
 Site        Share  Estimated to be delivered     Nds Nf  TB   End    Del Diff.
 ------------------+----------------------------+-------------+-----------
 IN2P3-LAPP:   25%   5.0MB/s 0.43TB/day 1.3TB/3d  129 217 0.78  2.319 4.0   1.67TB 
 IN2P3-CPPM:    5%   1.0MB/s 0.09TB/day 0.3TB/3d   23  39 0.14  0.108 0.977 0.87TB
 IN2P3-LPSC:    5%   1.0MB/s 0.09TB/day 0.3TB/3d   23  25 0.09  0.384 0.384 0.1TB
 IN2P3-LPC:    25%   5.0MB/s 0.43TB/day 1.3TB/3d  136 213 0.77  1.26  3.0   1.7TB
 BEIJING-LCG2: 20%   4.0MB/s 0.35TB/day 1.0TB/3d  102 159 0.57  5.557 6.359 0.8TB
 RO-07-NIPNE:  10%   2.0MB/s 0.17TB/day 0.5TB/3d   52  99 0.36  1.464 2.0   0.5TB
 RO-02-NIPNE:  10%   2.0MB/s 0.17TB/day 0.5TB/3d   39  69 0.25  2.625 2.831 >0.2TB
 GRIF-LAL:     45%   9.0MB/s 0.77TB/day 2.3TB/3d  231 310 1.12  3.5   5.844 2.3TB
 GRIF-LPNHE:   25%   5.0MB/s 0.43TB/day 1.3TB/3d  136 213 0.77  2.24  3.89  1.65TB
 GRIF-SACLAY:  30%   6.0MB/s 0.52TB/day 1.6TB/3d  144 248 0.89  3.623 5.905 2.3TB
 TOKYO-LCG2:  100%  20.0MB/s 1.73TB/day 5.2TB/3d  626 974 3.5   3.727 8.738 5TB 
 ------------------+----------------------------+-------------+-----------
 Total :      300%  60.0MB/s 5.18TB/day 15.6TB/3d

Something wrong with the estimate by dq2? Or, multiple replication of data counts this much?

cc-in2p3 
Lyo-cern-weekly.20080525-1058.gif
lyon-nord 
Lyo-nrd-weekly-20080525.gif
orsay 
in2p3-orsay.cssi.renater.fr

http://netstat.in2p3.fr/weathermap/graphiques/orsay-weekly.gif

lal 
Lal-cc-weekly-20080525.gif Lal-weekly-20080525.gif
lpnhe
Lpnhe-nrd-weekly-20080525.gif Lpsc-weekly-20080525.gif
lapp 
Ann-nrd-weekly-20080525.gif
lpc 
Lpc-cf-weekly-20080525.gif
lpsc 
lpsc
http://netstat.in2p3.fr/weathermap/graphiques/lpsc-weekly.gif
cppm 
Cppm-weekly-20080525.gif
international (tokyo etc.) 
Parisnrd-weekly.20080525.gif
GEANT - NYC 
GEANT-MANLAN-20080525.png
NYC - TOKYO 
MANLAN-SINET-20080525.png
tokyo 
ICEPP network-week-20080525.png Lcgse01.icepp.jp-w-20080525.png

Logbook

Attention! Graphs made by dashb might be wrong.


26 May

26 May 10h50

free space

 BEIJING-LCG2_DATADISK 6.366 6.366 6.359
 GRIF-LAL_DATADISK 6.0 6.0 5.81
 GRIF-LPNHE_DATADISK 3.906 3.906 3.89
 GRIF-SACLAY_DATADISK 6.0 6.0 5.905
 IN2P3-CPPM_DATADISK 1.0 1.0 0.977
 IN2P3-LAPP_DATADISK 4.0 4.0 4.0
 IN2P3-LPC_DATADISK 3.0 3.0 3.0
 IN2P3-LPSC_DATADISK 0.488 0.488 0.384
 RO-02-NIPNE_DATADISK 3.0 3.0 2.831
 RO-07-NIPNE_DATADISK 0 0 0
 TOKYO-LCG2_DATADISK 15.0 15.0 13.738


25 May

Attention! Graphs made by dashb might be wrong.

http://dashb-atlas-data.cern.ch/dashboard/request.py/site?name=LYON&fromDate=2008-05-25%2000:00&toDate=2008-05-26%2000:00

Throughput (MB/s) 
LYON.throughput.86400.20080525-1750.png
Volume (GB) 
LYON.total bytes xs.86400.20080525-1750.png
Number of files 
LYON.num file xs.86400.20080525-1750.png
Number of transfer errors 
LYON.num file xs error.86400.20080525-1750.png
25 May 22h50

free space

 BEIJING-LCG2_DATADISK 6.366 6.366 6.359
 GRIF-LAL_DATADISK 6.0 6.0 5.844
 GRIF-LPNHE_DATADISK 3.906 3.906 3.89
 GRIF-SACLAY_DATADISK 6.0 6.0 5.649
 IN2P3-CPPM_DATADISK 1.0 1.0 0.977
 IN2P3-LAPP_DATADISK 4.0 4.0 4.0
 IN2P3-LPC_DATADISK 3.0 3.0 3.0
 IN2P3-LPSC_DATADISK 0.488 0.488 0.384
 RO-02-NIPNE_DATADISK 3.0 3.0 2.635
 RO-07-NIPNE_DATADISK 2.0 2.0 2.0
 TOKYO-LCG2_DATADISK 10.0 10.0 5.064

Thus data volumes transferred this week are:

 BEIJING-LCG2_DATADISK 6.359 - 5.557 = 0.8TB
 GRIF-LAL_DATADISK 5.844 - 3.5 = 2.3 TB
 GRIF-LPNHE_DATADISK 3.89 - 2.24 = 1.65TB
 GRIF-SACLAY_DATADISK 5.649 - 3.623 = 2TB
 IN2P3-CPPM_DATADISK 0.977 - 0.108 = 0.87TB
 IN2P3-LAPP_DATADISK 4.0 - 2.319 = 1.67TB
 IN2P3-LPC_DATADISK 3.0 - 1.26 = 1.74TB
 IN2P3-LPSC_DATADISK 0.384 - 0.384 = ?
 RO-02-NIPNE_DATADISK : cannot estimate due to deletion errors
 RO-07-NIPNE_DATADISK 2.0 - 1.464 = 0.5TB
 TOKYO-LCG2_DATADISK : cannot estimate due to re-subscription 
25 May 14h00

Datasets re-subscribed to tokyo after deletion.

LYON.throughput.14400.20080525-1800.png
LYON.throughput.20080525-1100-1500.png
LYON.num file xs.20080525-1100-1500.png
LYON.total bytes xs.20080525-1100-1500.png

24 May

Attention! Graphs made by dashb might be wrong.

http://dashb-atlas-data.cern.ch/dashboard/request.py/site?name=LYON&fromDate=2008-05-24%2000:00&toDate=2008-05-25%2000:00

Throughput (MB/s) 
LYON.throughput.20080524.png
Volume (GB) 
LYON.total bytes xs.20080524.png
Number of files 
LYON.num file xs.20080524.png
Number of transfer errors 
LYON.num file xs error.20080524.png

These graphs show from 01h to 01h, but in fact, the contents are from 00h to 00h.

Since the new shares were applied (around midnight), 3.5TB of data were transferred in 2 hours. That is, the shares were applied also to all the ccrc08_run2 data in the past.

Attention! Graphs made by dashb might be wrong.

Number of files as snapshot of "last 24h" at 19h46 
LYON.num file xs.86400.20080524-1946.png
Number of transfer errors 
LYON.num file xs error.86400.20080524.png
Number of transfer errors 
LYON.num file xs error.86400.20080524-1946.png


24 May 23h50

free space

 BEIJING-LCG2_DATADISK 6.366 6.366 5.557
 GRIF-LAL_DATADISK 6.0 6.0 3.5
 GRIF-LPNHE_DATADISK 3.906 3.906 2.24
 GRIF-SACLAY_DATADISK 6.0 6.0 3.623
 IN2P3-CPPM_DATADISK 1.0 1.0 0.108
 IN2P3-LAPP_DATADISK 4.0 4.0 2.319
 IN2P3-LPC_DATADISK 3.0 3.0 1.26
 IN2P3-LPSC_DATADISK 0.488 0.488 0.384
 RO-02-NIPNE_DATADISK 3.0 3.0 2.625
 RO-07-NIPNE_DATADISK 2.0 2.0 1.464
 TOKYO-LCG2_DATADISK 10.0 10.0 3.727

datasets

 BEIJING-LCG2_DATADISK 102 
 GRIF-LAL_DATADISK 231 
 GRIF-LPNHE_DATADISK 136 
 GRIF-SACLAY_DATADISK 144 
 IN2P3-CPPM_DATADISK 23 
 IN2P3-LAPP_DATADISK 129 
 IN2P3-LPC_DATADISK 136 
 IN2P3-LPSC_DATADISK 23 
 RO-02-NIPNE_DATADISK 39 
 RO-07-NIPNE_DATADISK 52 
 TOKYO-LCG2_DATADISK 626 


24 May 14h00

Since 11h10-20, T0 exports are resumed, still with some errors but much less. the overall rate (T0-T1 but to Lyon) went over 1000MB/s, and sustained >900MB/s untill 12h10. then started decreasing. likely T0 load generation has stopped.


24 May 07h30

apparently, srm.cern.ch is down since 2008-05-24 06:56:26 (dashb). GGUS-Ticket 36761 has been created.

 [FTS] FTS State [Failed] FTS Retries [1] Reason [SOURCE error during PREPARATION phase: [GENERAL_FAILURE] Error caught in srm::getSrmUser.Error creating statement, Oracle code: 18ORA-00018: maximum number of sessions exceeded] Source Host [srm-atlas.cern.ch]

In fact, it may not be down, but just too busy with too many accesses. Seems to have recovered 07h50. But down again? 08h30.

Throughput 
OVERVIEW.throughput.14400.20080524-0836.png
Errors 
OVERVIEW.num file xs error.14400.20080524-0836.png


24 May 00h14

Stephane noticed the new shares had been applied. It seems the subscriptions are made taking all the ccrc08_run2 data into account, not only from now on. That is, we will get much more data and rate than is expected from the shares.

Throughput 
LYON.T2.throughput.14400.20080524-0300.png
Errors 
LYON.num file xs error.14400.20080524-0300.png

Most of the errors are for IN2P3-CC_DATADISK (305: can't see the cause on dashb), IN2P3-CC_DATATAPE (168: can't see the cause on dashb), IN2P3-CC_MCDISK (80: source error at bnl), RO-02-NIPNE_DATADISK (33: TRANSFER_TIMEOUT, PERMISSION)

LPC 
Lpc-cf-daily.20080524-120109.gif

23 May

Throughput

LYON.throughput.20080523.png

Errors

LYON.num file xs error.20080523.png

23 May 20h00

many failures to IN2P3-CC_MCDISK. with

 Source Host [dcsrm.usatlas.bnl.gov].

now that T0-LYON transfers are also on production dashb, such errors are not nice in monitoring the ccrc transfers. GGUS-Ticket 36755 has been created.

23 May 08h20

Beijing has started working since 01:44, although with a number of errors until 07:43.

 [FTS] FTS State [Failed] FTS Retries [1] Reason [TRANSFER error during TRANSFER phase: [TRANSFER_TIMEOUT] gridftp_copy_wait: Connection timed out] Source Host [ccsrm.in2p3.fr]

after the last error at 07:43, transfers seem going well.

RO-02-NIPNE_DATADISK also working from time to time. still with many errors

22 May

Throughput

LYON.throughput.20080522.png

Errors

LYON.num file xs error.20080522.png

  • There was a network problem for Romanian national Internet provider RoEdu from 6:30 to 10 GMT, according to Titi and Mihai.


22 May 22h50

Transfers to RO-02-NIPNE_DATADISK have been failing. GGUS-Ticket 36728 has been created.

Otherwise, transfers are going well except for BEIJING.

22 May 14h50

One file assigned to CPPM has a source problem;

Received error message: SOURCE error during PREPARATION phase: [REQUEST_TIMEOUT] failed to prepare source file in 180 seconds

with srm://marsedpm.in2p3.fr:8446/srm/managerv2?SFN=/dpm/in2p3.fr/home/atlas/atlasdatadisk/ccrc08_run2/AOD/ccrc08_run2.016765.physics_C.merge.AOD.o0_r0_t0/ccrc08_run2.016765.physics_C.merge.AOD.o0_r0_t0._0001__DQ2-1211460721

GGUS-Ticket 36709 has been created. https://gus.fzk.de/pages/ticket_details.php?ticket=36709


22 May 14h20

the T0->LYON export was migrated from T0 VOBOX to LYON VOBOX. Transfers T0->LYON should be monitored with the Production dashboard http://dashb-atlas-data.cern.ch/dashboard/request.py/site?name=LYON


22 May 13h05

Titi: Unfortunately there was an unscheduled network breakdown in our institute started from about 6:30 to 10 GMT.


22 May 12h40

Stephane switched back the certificate from Kors' certificate to Mario's.

Then again seeing problems, went again with Kors'.


22 May 10h29

starting 09:21:35, there are errors in transfers to RO-07-NIPNE_DATADISK in dashb.

 [FTS] FTS State [Failed] FTS Retries [1] Reason [DESTINATION error during PREPARATION phase: [CONNECTION] failed to contact on remote SRM [httpg://tbit00.nipne.ro:8446/srm/managerv2]. Givin' up after 3 tries] Source Host [ccsrm.in2p3.fr]

GGUS-Ticket 36698 created

24 May 2008 11:35, Mihai: Sorry for this problem.But this was happening because of a problem occurred to our national Internet provider RoEdu.


22 May 09h40

According to Alexei, cron job for subscription to T2s does not run frequently during the night. That is why.


22 May 09h00

transfers T1-T2 resumed since 8h30. reaching 900MB/s in total.

numbers of assigned datasets to sites look better now.

Killed a MC data subscription to RO-07-NIPNE_MCDISK.


22 May 08h00

T0-T1 transfers are proceeding, No T1-T2 transfers to DATADISK since last night.

according to dq2.log, new subscriptions today (since 5.22 00:00) are queued only to BEIJING and RO-02-NIPNE, resulting in errors.

the status table does not look nice, I will check. http://panda.atlascomp.org/?mode=listFunctionalTests&testType=T1toT2s#LYON

apparently, no subscription to LAPP, CPPM, LPSC. TOKYO and LAL, who are assigned larger shares, have less subscriptions.

21 May

Attention! dashb shows wrong results http://dashb-atlas-data.cern.ch/dashboard/request.py/site?name=LYON&fromDate=2008-05-21%2000:00&toDate=2008-05-22%2000:00

And the graphs can also be wrong

Throughput all T0-T1

OVERVIEW.throughput.20080521.png

Throughtput T0-LYON

LYON.throughput.20080521-1.png

Throughput LYON-T2

LYON.T2.throughput.20080521.png


21 May 23h30

There are many errors in transfers to NIPNE02

 DESTINATION error during PREPARATION phase: [PERMISSION]


21 May 22h30

Stephane found a temporary solution for the LFC problem. It does not accept Mario's certificate, but does Kors' (thus no problem in T0-T1 transfers).

the dashb graphs show these transfers as of 19:xx (transfers done at 19:xx = 17:xx UTC, and registration done at around 22:30)


21 May 20h20

dashb shows transfers, which seem to be successful but with many registration errors, in the table (not in the graph). Looking into the details, file states are 'ATTEMPT_DONE' with 'HOLD_FAILED_REGISTRATION'

LYON.T2.throughput.14400.20080521-2028.png

the time on ftsmonitor is UTC.


21 May 19h30

Finally 19 more subscriptions appeared in the dq2.log.

  • ccrc08_run2.016731.physics_D.merge.AOD.o0_r0_t0 (2 files) to BEIJING-LCG2_DATADISK and GRIF-SACLAY_DATADISK
  • ccrc08_run2.016730.physics_B.merge.AOD.o0_r0_t0 (2 files) to BEIJING-LCG2_DATADISK and GRIF-SACLAY_DATADISK
  • ccrc08_run2.016730.physics_D.merge.AOD.o0_r0_t0 (2 files) to BEIJING-LCG2_DATADISK and GRIF-SACLAY_DATADISK

and so on.

In the dq2.log, the files got FileTransferring, VALIDATED, FileCopied, but then, there are errors

FileTransferErrorMessage : reason = [FTS] FTS State [Failed] FTS Retries [1] Reason [TRANSFER error during TRANSFER phase: [TRANSFER_TIMEOUT] globus_gass_copy_register_url_to_url: Connection timed out]
FileRegisterErrorMessage : reason = LFC exception [Cannot connect to LFC [lfc://lfc-prod.in2p3.fr:/grid/atlas]]
21 May 18h20 

Around 17h30 transfers resumed. Rate for 17h40-18h20: IN2P3-CC_DATADISK: 158 MB/s, IN2P3-CC_DATATAPE: 37 MB/s

no subscriptions/transfers T1-T2 since the very first dataset ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 (vuid = 6403bd5a-5a71-4732-9a0a-b22b56aef106) to GRIF-LAL_DATADISK and TOKYO-LCG2_DATADISK. Transfers to Tokyo has finished. LAL is still Inactive.

21 May 16h40
Since around 16:40 T0-T1 transfers stopped. There are many errors.

SOURCE error during PREPARATION phase: [GENERAL_FAILURE] 
Error caught in srm::getSrmUser.Error creating statement, 
Oracle code: 12537ORA-12537: TNS:connection closed] 
Source Host [srm-atlas.cern.ch]
OVERVIEW.throughput.14400.20080521-1300-1700.png
OVERVIEW.num file xs error.14400.20080521-1300-1700.png
LYON.throughput.14400.20080521-1300-1700.png
LYON.num file xs error.14400.20080521-1300-1700.png



21 May 13h30
T0-T1 Transfers started at around 13h30. The overall throughput from T0 is over 1000MB/s. Lyon is receiving its share at 100-200 MB/s (verying with time). the average rate is about 40MB/s to IN2P3-CC_DATADISK and 140MB/s to IN2P3-CC_DATATAPE according to dashb http://dashb-atlas-data-tier0.cern.ch/dashboard/request.py/site?name=LYON.

20080521-1530-OVERVIEW.throughput.14400.png
20080521-1530-LYON.throughput.14400.png

T1-T2 Transfers started at around 15h10. http://lcg2.in2p3.fr/wiki/images/20080521-1530-LYONT2.throughput.14400.png

  • from dq2.log:
    • 2008-05-21 15:00: SubscriptionQueued for dataset ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 (vuid = 6403bd5a-5a71-4732-9a0a-b22b56aef106) to GRIF-LAL_DATADISK and TOKYO-LCG2_DATADISK
    • 2008-05-21 15:00: FileTransferring: 3 files of the dataset ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 (fsize = 3600000000 each) for both TOKYO-LCG2_DATADISK and GRIF-LAL_DATADISK
    • 2008-05-21 15:03: VALIDATED: 3 files of dataset ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 at srm://lcg-se01.icepp.jp
    • 2008-05-21 15:03: FileCopied: 3 files of dataset ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 at TOKYO-LCG2_DATADISK
    • 2008-05-21 15:03: FileDone: 3 files of dataset ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 at TOKYO-LCG2_DATADISK
    • 2008-05-21 15:05: SubscriptionComplete: vuid = 6403bd5a-5a71-4732-9a0a-b22b56aef106 : site = TOKYO-LCG2_DATADISK : dsn = ccrc08_run2.016731.physics_A.merge.AOD.o0_r0_t0 : version = 1
  • FTS channels for LAL are 'Inactive' for 'Pb clim LAL'

Extra tests

GRIF (26 May)

26 May 12h50
Througput (MB/s) 
LYON.T2.throughput.14400.20080526-1250.png
Errors 
LYON.T2.num file xs error.14400.20080526-1250.png
26 May 12h14
Througput (MB/s) 
LYON.T2.throughput.14400.20080526-1214.png
Errors 
LYON.T2.num file xs error.14400.20080526-1214.png

BEIJING (26 May)

27 May 14h15

Erming:

 I tuned the IN2P3-BEIJING channel to 20 concurrent files and 5 concurrent streams. I tested many combinations:
 Nofiles   NoStreams
 5            3
 10           5
 15           5
 20           5
 20           10
 25           5
 30           5
 
 It appears that 20/5 is the best for the moment which can reach more than 80MB/s throughput.


26 May

Number of concurrent files increased, and tested.

Throughput (MB/s)
LYON.T2.throughput.20080526-1710-2110.png
Errors
LYON.T2.num file xs error.20080526-1710-2110.png

T0-T1-T2 + T1-T1 transfer + MC production (week4)

Plan

ADC Oper 22 May (slide 8 - 10) http://indico.cern.ch/materialDisplay.py?contribId=3&materialId=slides&confId=34556

Friday morning: data generation stops


T0-T1-T2 
Datasets named ccrc08_run2.018* produced at the nominal rate
T1-T1 
Datasets named ccrc08_run2.017* (ESD+AOD only, no RAW) produced at the nominal rate (up to 29 May in the morning).
The ESDs are replicated only between the paired T1s during the first two days. AODs are replicated to everywhere.
Datasets named ccrc08_run2.019* (ESD+AOD only, no RAW) produced at the nominal rate (since 29 May in the morning)
The ESDs are replicated from every T1 to every other T1s for the last two days.
 nominal rate = 200Hz * 14h/day = 10 M events/day
 
 RAW: 1.6 MB/event, nominal 16TB/day
 ESD: 1.0 MB/event, nominal 10TB/day
 AOD: 0.1 MB/event, nominal  1TB/day
 
 LYON T1
   RAW: in from T0: 15% nominal = 2.4TB/day
 
   ESD: in from T0: 15%+15% nominal = 3TB/day
        in from partner T1 (60% of BNL): 15% nominal = 1.5TB/day (at first)
        in from all other T1: 85% nominal = 8.5TB/day (later)
        out to partner T1: 15% nominal = 1.5TB/day (at first)
        out to all other T1: 9*15% nominal = 13.5TB/day (later)
 
   AOD: in from T0: 100%+15% nominal = 1.15TB/day
        in from other T1s: 85% nominal = 0.85TB/day
        out to all other T1s: 9 * 15% nominal = 1.35TB/day
        out to T2s: 100% nominal * sum(T2 shares) = 1TB*sum(T2shares)/day
 
   total in: 2.4TB/day on tape, 28MB/s, 9.6TB/4d
         in: 6.5TB/day on disk, 75MB/s, 26TB/4d (first)
         in: 13.5TB/day on disk, 156MB/s (later)
         out to T1s 2.85TB/day,  33MB/s (first)
         out to T1s 15TB/day, 172MB/s (later)
         out to T2s 1*sum(T2 shares) TB/day,  12*sum(T2 shares) MB/s
subscription cron

Datasets are subscribed to T1s from partner Tier-1s ~ every 2h

Datasets are subscribed to T2s from parent Tier-1s ~ every 4h

T0 - T1

T1 - T2

  • Shares requested for the T2s, and data volume estimation done by I.Ueda
   * IN2P3-LAPP_DATADISK :   25%  0.25TB/d,  2.9MB/s,  1.0TB/4d
   * IN2P3-CPPM_DATADISK :    5%  0.05TB/d,  0.6MB/s,  0.2TB/4d
   * IN2P3-LPSC_DATADISK :    5%  0.05TB/d,  0.6MB/s,  0.2TB/4d
   * IN2P3-LPC_DATADISK :    25%  0.25TB/d,  2.9MB/s,  1.0TB/4d
   * BEIJING-LCG2_DATADISK : 20%  0.20TB/d,  2.3MB/s,  0.8TB/4d
   * RO-07-NIPNE_DATADISK :  10%  0.10TB/d,  1.2MB/s,  0.4TB/4d
   * RO-02-NIPNE_DATADISK :  10%  0.10TB/d,  1.2MB/s,  0.4TB/4d
   * GRIF-LAL_DATADISK :     45%  0.45TB/d,  5.2MB/s,  1.8TB/4d
   * GRIF-LPNHE_DATADISK :   25%  0.25TB/d,  2.9MB/s,  1.0TB/4d
   * GRIF-SACLAY_DATADISK :  30%  0.30TB/d,  3.5MB/s,  1.2TB/4d
   * TOKYO-LCG2_DATADISK :  100%  1.0 TB/d, 11.6MB/s,  4.0TB/4d
   ------------------------------------------------------------------
     Total :                300%  3.0 TB/d, 34.7MB/s, 12.0TB/4d
  • Tue, 27 May 2008 17:17:29 +0200, From: Alexei Klimentov
 - subscriptions from T1 to parent T2s are done every 3-4h
 - local file catalogs are checked every 2h
 http://pandamon.usatlas.bnl.gov:25880/server/pandamon/query?mode=listFunctionalTests&testType=T1toT2s
 There were several requests to change '%%' 
 I attach the last table I am using (there are 48 T2s participating)
  line  INFN-FRASCATI_DATADISK  |         25 |  INFN-MILANO_DATADISK
  means that INFN-FRASCATI_DATADISK will be subscribed to 25% of AODs 
  from CNAF and datasets@FRASCATI shouldn't overlap with the 
  datasets@MILANO
 
 Subscriptions are done using my certificate
Alexei's table for T2s
 GRIF-LAL_DATADISK	45	GRIF-LPNHE_DATADISK,GRIF-SACLAY_DATADISK
 GRIF-LPNHE_DATADISK	25	GRIF-SACLAY_DATADISK,GRIF-LAL_DATADISK
 GRIF-SACLAY_DATADISK	30	GRIF-LPNHE_DATADISK,GRIF-LAL_DATADISK
 IN2P3-CPPM_DATADISK	5	IN2P3-LAPP_DATADISK,IN2P3-LPSC_DATADISK,IN2P3-LPC_DATADISK,BEIJING-LCG2_DATADISK,RO-02-NIPNE_DATADISK,RO-07-NIPNE_DATADISK
 IN2P3-LAPP_DATADISK	25	IN2P3-CPPM_DATADISK,IN2P3-LPSC_DATADISK,IN2P3-LPC_DATADISK,BEIJING-LCG2_DATADISK,RO-02-NIPNE_DATADISK,RO-07-NIPNE_DATADISK
 IN2P3-LPC_DATADISK	25	IN2P3-LAPP_DATADISK,IN2P3-CPPM_DATADISK,IN2P3-LPSC_DATADISK,BEIJING-LCG2_DATADISK,RO-02-NIPNE_DATADISK,RO-07-NIPNE_DATADISK
 IN2P3-LPSC_DATADISK	5	IN2P3-LAPP_DATADISK,IN2P3-CPPM_DATADISK,IN2P3-LPC_DATADISK,BEIJING-LCG2_DATADISK,RO-02-NIPNE_DATADISK,RO-07-NIPNE_DATADISK
 RO-02-NIPNE_DATADISK	10	IN2P3-LAPP_DATADISK,IN2P3-CPPM_DATADISK,IN2P3-LPSC_DATADISK,IN2P3-LPC_DATADISK,BEIJING_DATADISK,RO-07-NIPNE_DATADISK
 RO-07-NIPNE_DATADISK	10	IN2P3-LAPP_DATADISK,IN2P3-CPPM_DATADISK,IN2P3-LPSC_DATADISK,IN2P3-LPC_DATADISK,BEIJING_DATADISK,RO-02-NIPNE_DATADISK
 TOKYO-LCG2_DATADISK	100	IN2P3-LAPP_DATADISK,IN2P3-CPPM_DATADISK,IN2P3-LPSC_DATADISK

T1 - T1

  • Date: Tue, 27 May 2008 17:17:29 +0200, From: Alexei Klimentov
 - subscriptions are done every 2h
 - local file catalogs are checked every hour
 http://pandamon.usatlas.bnl.gov:25880/server/pandamon/query?mode=listFunctionalTests&testType=T1toT1s
 ESD subscriptions 
   BNL : all ccrc08_run2.0170*ESD* datasets 
   Other sites :
    line | FZK-LCG2_DATADISK      |         40 | BNL-OSG2_DATADISK      |
    means FZK is subscribed to 40% of ccrc08_run2.0170*ESD* from BNL
    (important, 40% calculated from the number of completed datasets 
     at BNL)
    40% at FZK and 60% at LYON shouldn't overlap
    (ditto, for INFN and NIKHEF)
    subscription is done with '--source' and w/o '--wait-for-source' 
    options
    subscriptions are done using Kors cert
 
 +------------------------+------------+------------------------+
 | tier1                  | percentage | tier1_pair             |
 +------------------------+------------+------------------------+
 | FZK-LCG2_DATADISK      |         40 | BNL-OSG2_DATADISK      |
 | IN2P3-CC_DATADISK      |         60 | BNL-OSG2_DATADISK      |
 | INFN-T1_DATADISK       |         50 | RAL-LCG2_DATADISK      |
 | NDGF-T1_DATADISK       |        100 | PIC_DATADISK           |
 | NIKHEF-ELPROD_DATADISK |         50 | RAL-LCG2_DATADISK      |
 | PIC_DATADISK           |        100 | NDGF-T1_DATADISK       |
 | RAL-LCG2_DATADISK      |        100 | INFN-T1_DATADISK       |
 | RAL-LCG2_DATADISK      |        100 | NIKHEF-ELPROD_DATADISK |
 | TAIWAN-LCG2_DATADISK   |        100 | TRIUMF-LCG2_DATADISK   |
 | TRIUMF-LCG2_DATADISK   |        100 | TAIWAN-LCG2_DATADISK   |
 +------------------------+------------+------------------------+

Logbook

Fri, 30 May

30 May 9h00
The plan was to stop the data generation at T0 during the morning, but there was a CERN wide powercut (see http://cern.ch/ssb), so this is the end of the generation. We just wait and see all the subscriptions to be processed and replication to be completed.
A snapshot will be taken at noon tomorrow, and then all the ccrc08_run2 data will be deleted.

Thu, 29 May

29 May 9h30
http://cern.ch/ssb ATLAS Castor SRM service intervention between 9:00 and 10:00 am The ATLAS Castor SRM service will be down for one hour to move the backend database to more powerful hardware. There will be no WAN transfers for ATLAS during this period. The rest of Castor ATLAS will not be affected.


29 May 9h30 
load generator for T1-T1 datasets has switched from run 017 to run 019.
Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.14400.20080529-1500.png
Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.14400.20080529-1100.png
Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.14400.20080529-0700.png
Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.14400.20080529-0300.png

Wed, 28 May

Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.86400.20080529-0100.png
Data volume transferred (GB)
Atlas-dashb-prod-LYON.T2.total bytes xs.86400.20080529-0100.png
Number of files transferred
Atlas-dashb-prod-LYON.T2.num file xs.86400.20080529-0100.png
Number of errors in transfers
Atlas-dashb-prod-LYON.T2.num file xs error.86400.20080529-0100.png


28 May 13h00 
Being bothered by MC transfer errors with 'file not found' at the source sites (BNLPANDA, NDGFT1DISK), sent Savannah bug items 37054, 37055


28 May 11h15 
In the last 24h;
                       Transfers
 Site                  Eff.    Succ.   Errors
 BEIJING-LCG2_DATADISK	75%	134	45
 GRIF-LAL_DATADISK	94%	150	10
 GRIF-LPNHE_DATADISK	99%	99	1
 GRIF-SACLAY_DATADISK	100%	100	0
 IN2P3-CPPM_DATADISK	100%	18	0
 IN2P3-LAPP_DATADISK	99%	95	1
 IN2P3-LPC_DATADISK	100%	101	0
 IN2P3-LPSC_DATADISK	100%	22	0
 RO-02-NIPNE_DATADISK	34%	28	55
 RO-07-NIPNE_DATADISK	100%	38	0
 TOKYO-LCG2_DATADISK	98%	319	7
[TRANSFER error during TRANSFER phase: [GRIDFTP] the server sent an error response: 426 426 Transfer aborted (Unexpected Exception : java.io.IOException: Broken pipe)] [TRANSFER error during TRANSFER phase: [TRANSFER_TIMEOUT] gridftp_copy_wait: Connection timed out] [TRANSFER error during TRANSFER phase: [TRANSFER_TIMEOUT] globus_gass_copy_register_url_to_url: Connection timed out] [SOURCE error during TRANSFER phase: [TRANSFER_TIMEOUT] globus_ftp_client_size: Connection timed out] [TRANSFER error during TRANSFER phase: [GRIDFTP] an end-of-file was reached (possibly the destination disk is full)] [TRANSFER error during TRANSFER phase: [PERMISSION] the server sent an error response: 550 550 rfio write failure: Permission denied.]
BEIJING-LCG2_DATADISK 15 14 14 1 1
GRIF-LAL_DATADISK 2 7 4
GRIF-LPNHE_DATADISK 1
IN2P3-LAPP_DATADISK 1
RO-02-NIPNE_DATADISK 2 48 1 4
TOKYO-LCG2_DATADISK 4 3
28 May 09h00 
Transfers to T2s are going well.

Atlas-ListT1T2-20080528-0801.png

Tue, 27 May

Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.86400.20080528-0100.png
Volume transferred (GB)
Atlas-dashb-prod-LYON.T2.total bytes xs.86400.20080528-0100.png
Number of files transferred
Atlas-dashb-prod-LYON.T2.num file xs.86400.20080528-0100.png
Number of errors in transfers
Atlas-dashb-prod-LYON.T2.num file xs error.86400.20080528-0100.png


27 May 16h40 
  • BEIJING has had 11
    [TRANSFER error during TRANSFER phase: [TRANSFER_TIMEOUT] globus_gass_copy_register_url_to_url: Connection timed out]
  • RO-02-NIPNE had 7
    [TRANSFER error during TRANSFER phase: [TRANSFER_TIMEOUT] gridftp_copy_wait: Connection timed out]
  • and 1
    [SOURCE error during TRANSFER phase: [TRANSFER_TIMEOUT] globus_ftp_client_size: Connection timed out]
  • TOKYO-LCG2: 1
    [SOURCE error during TRANSFER phase: [TRANSFER_TIMEOUT] globus_ftp_client_size: Connection timed out]
Number of Files Transferred
Atlas-dashb-prod-LYON.T2.num file xs.14400.20080527-1700.png
Errors
Atlas-dashb-prod-LYON.T2.num file xs error.14400.20080527-1700.png


27 May 14h00 
We reached nearly 700MB/s in total
Throughput (MB/s)
Atlas-dashb-prod-LYON.T2.throughput.14400.20080527-14.png
Errors
Atlas-dashb-prod-LYON.T2.num file xs error.14400.20080527-14.png


27 May 11h40 
The T1-T2 transfers have started
27 May 09h50 
The T0 data generation has started already yesterday.

The T0 export is being started. (That is, there is a large backlog for T0-T1.)

Mon, 26 May

26 May 20h00 
Still don't see any ccrc08_run2 datasets being transferred. (the activities for T0-T1 are data08_cosm7).


26 May 18h50 
around 18h50 T0-LYON transfers went back to T0 vobox, monitored by T0 dashb.


26 May 15h40 
cosmic data transfers ongoing (data08_cosm7, T0-T1) need to wait still more before ccrc data to come out.