Introduction

Collaboration between Pegasus and the Center for Enabling Distributed Petascale Science (CEDPS) troubleshooting project, whose software is almost all part of NetLogger. For the converse, see the Pegasus page on the CEDPS wiki.
http://www.cedps.net/index.php/Pegasus/Kickstart_Log_Processing

PEGASUS SVN

https://smarty.isi.edu/svn/repo1/pegasus/trunk

the new parser is called contrib/showlog/gensim

SCEC RUNS

START and END TIMES OF RUNS

for site in USC SABD LADT WNGC FFI CCP SBSM SMCA LBP; do
{panel}
   echo "Site $site";
   mysql -u dbuser -ppwd -h isis.isi.edu  cybershk_july_2008_2 -e
  "select  MIN(from_unixtime(time)) as START, MAX(from_unixtime(time)) as END from event
   join ident on event.id=ident.e_id WHERE ident.value LIKE 'CyberShake_${site}%'";
  echo "";echo""; done;
{panel}
Site USC
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-07 16:59:46 | 2008-07-08 10:17:51 |
+---------------------+---------------------+


Site SABD
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-13 08:24:20 | 2008-07-14 00:53:58 |
+---------------------+---------------------+


Site LADT
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-12 13:08:23 | 2008-07-13 12:41:09 |
+---------------------+---------------------+


Site WNGC
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-11 18:52:22 | 2008-07-13 16:56:21 |
+---------------------+---------------------+


Site FFI
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-17 13:02:01 | 2008-07-18 10:29:12 |
+---------------------+---------------------+


Site CCP
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-16 21:17:59 | 2008-07-17 11:59:24 |
+---------------------+---------------------+


Site SBSM
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-16 07:47:14 | 2008-07-17 08:45:11 |
+---------------------+---------------------+


Site SMCA
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-15 13:06:01 | 2008-07-16 02:15:15 |
+---------------------+---------------------+


Site LBP
+---------------------+---------------------+
| START               | END                 |
+---------------------+---------------------+
| 2008-07-14 10:34:11 | 2008-07-15 13:02:48 |
+---------------------+---------------------+

Complete RUNS July 2008

( With kickstart outputs /jobstate.log )

USC_PP

Netlogger Statistics

TRANSFORMATION

number

sum_seconds

sum_hours

avg_seconds

failures

pegasus::dirmanager

40

24.75

0.01

0.62

0

pegasus::rc-client

80

207.61

0.06

2.6

0

pegasus::transfer

384

66492.13

18.47

173.16

264

scec::extract_sgt:1.0

7000

1082070.75

300.58

154.58

0

scec::PeakValCalc_Okaya:1.0

417886

630647.75

175.18

1.51

0

scec::seismogram_synthesis:1.0

417886

26980412.48

7494.56

64.56

0

scec::ZipPeakSA:1.0

40

55347.38

15.37

1383.68

0

scec::ZipSeismograms:1.0

40

57728.22

16.04

1443.21

0

TOTALS

843356

28872931.07

8020.27

264

TRANSFORMATION	failures

pegasus::transfer 	264


Time to load to Gaurang Mac
2 hours 34 minutes

Gensim Statistics

AVERAGES

Job Type

Job Count

Condor Delay

Dagman Delay

Seqexec Delay

Postscript Time

Internal Time

Stage_in

0

NO ENTRIES

extract_sgt

0

NO ENTRIES

merge_scec-extract_sgt

2348

198.27

173.02

19.88

5.18

480.73

merge_scec-seismogram_synthesis

10464

515.48

504.24

771.68

5.02

3350.08

merge_scec-PeakValCalc_Okaya

2107

541.6

94.79

1610.77

5.01

1910.08

Zip

80

321.93

5.12

0

5.01

1413.45

stage_out

0

NO ENTRIES

other jobs

280

59.37

2406.35

0

4.31

208.01

TOTALS

Job Type

Job Count

Condor Delay

Dagman Delay

Seqexec Delay

Postscript Time

Internal Time

stage_in

0

0

0

0

0

0

extract_sgt

0

0

0

0

0

0

merge_scec-extract_sgt

2348

465544

406248

46674.47

12168

1128745.22

merge_scec-seismogram_synthesis

10464

5394026

5276328

8074868.93

52565

35055281.69

merge_scec-PeakValCalc_Okaya

2107

1141157

199729

3393894.22

10563

4024542.21

Zip

80

25754

410

0

401

113075.61

stage_out

0

0

0

0

0

0

other jobs

280

16623

673779

0

1207

58242.78

Total (sec):

15279

7043104

6556494

11515437.62

76904

40379887.5

Total (hr):

15279

1956.42

1821.25

3198.73

21.36

11216.64

Percent:

10.74%

10.00%

17.56%

0.12%

61.58%

RUNS July 2008 ( Only the kickstart output files )

CCP_PP

FFI_PP

LADT_PP

LBP_PP

SABD_PP

SBSM_PP

SMCA_PP

USC_PP

WNGC_PP

MONTAGE RUNS

Cloud Runs

LIGO RUNS

Netlogger Debugger for Workflows

Netlogger Workflow Debugger

Troubleshooting

NetloggerTroubleshootingAPI

  • No labels