From 4c374c647d8fecce827cabcb579e5aae20f198db Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Mon, 27 Aug 2018 14:31:36 -0700 Subject: crude job stats/metrics in a text file --- notes/job_log.txt | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 95 insertions(+) create mode 100644 notes/job_log.txt (limited to 'notes') diff --git a/notes/job_log.txt b/notes/job_log.txt new file mode 100644 index 0000000..3cd16f0 --- /dev/null +++ b/notes/job_log.txt @@ -0,0 +1,95 @@ + +### QA matchcrossref + +[D8C7F2CA7620450991838D540489948D/8B17786779BE44579C98D8A325AC5959] sandcrawler.ScoreJob/(1/1) ...-24-2102.32-matchcrossref + +Submitted: Fri Aug 24 21:03:09 UTC 2018 +Started: Fri Aug 24 21:03:20 UTC 2018 +Finished: Sat Aug 25 09:46:55 UTC 2018 +Elapsed: 12hrs, 43mins, 34sec +Diagnostics: +Average Map Time 24mins, 31sec +Average Shuffle Time 15sec +Average Merge Time 21sec +Average Reduce Time 7mins, 17sec + +Map 2312 2312 +Reduce 100 100 + +crossref-rows-filtered 73901964 0 73901964 +grobid-rows-filtered 1092992 0 1092992 +joined-rows 0 623837 623837 + +cascading.flow.StepCounters +Tuples_Read 94831255 0 94831255 +Tuples_Written 0 623837 623837 + +Read_Duration 7108430 352241 7460671 +Tuples_Read 94831255 74994956 169826211 +Tuples_Written 74994956 623837 75618793 +Write_Duration 7650302 21468 7671770 + +## QA UnGrobided + +Submitted: Sat Aug 25 01:23:22 UTC 2018 +Started: Sat Aug 25 05:06:36 UTC 2018 +Finished: Sat Aug 25 05:13:45 UTC 2018 +Elapsed: 7mins, 8sec +Diagnostics: +Average Map Time 1mins, 20sec +Average Shuffle Time 12sec +Average Merge Time 15sec +Average Reduce Time 29sec + +Map 48 48 +Reduce 1 1 + +bnewbold@bnewbold-dev$ gohdfs du -sh sandcrawler/output-qa/2018-08-25-0122.54-dumpungrobided/part* +56.8M /user/bnewbold/sandcrawler/output-qa/2018-08-25-0122.54-dumpungrobided/part-00000 + +## Prod UnGrobided + +[D76F6BF91D894E879E747C868B0DEDE7/394A1AFC44694992B71E6920AF8BA3FB] sandcrawler.DumpUnGrobidedJob/(1/1) ...26-0910.25-dumpungrobided + +Map 278 278 +Reduce 1 1 + +Submitted: Sun Aug 26 09:10:51 UTC 2018 +Started: Sun Aug 26 09:18:21 UTC 2018 +Finished: Sun Aug 26 10:29:28 UTC 2018 +Elapsed: 1hrs, 11mins, 7sec +Diagnostics: +Average Map Time 4mins, 48sec +Average Shuffle Time 24mins, 17sec +Average Merge Time 14sec +Average Reduce Time 13mins, 54sec + + +cading.flow.StepCounters +Name +Map +Reduce +Total +Tuples_Read 64510564 0 64510564 +Tuples_Written 0 21618164 21618164 + +## Prod Crossref Match + +[6C063C0809244446BA8602C3BE99CEC2/5FE5D87899154F38991A1ED58BEB34D4] sandcrawler.ScoreJob/(1/1) ...-25-1753.01-matchcrossref + +Map 2427 2427 +Reduce 50 50 + +Submitted: Sat Aug 25 17:53:50 UTC 2018 +Started: Sat Aug 25 17:53:59 UTC 2018 +Finished: Sun Aug 26 11:22:52 UTC 2018 +Elapsed: 17hrs, 28mins, 52sec +Diagnostics: +Average Map Time 31mins, 20sec +Average Shuffle Time 1mins, 21sec +Average Merge Time 41sec +Average Reduce Time 3hrs, 14mins, 39sec + +crossref-rows-filtered 73901964 0 73901964 +grobid-rows-filtered 14222226 0 14222226 +joined-rows 0 14115453 14115453 -- cgit v1.2.3