Line | |
---|
1 | -- This script processes failure cause for different categories of events grouped by duration (short, medium, long) |
---|
2 | |
---|
3 | -- author: cristina |
---|
4 | |
---|
5 | REGISTER failurecausefunc.jar; |
---|
6 | |
---|
7 | raw = LOAD '$inputDir/event_trace.tab' USING PigStorage('\t') AS (event_id,component_id,node_id,platform_id,node_name,event_type,event_start_time,event_stop_time,event_end_reason:chararray); |
---|
8 | |
---|
9 | -- build durations |
---|
10 | duration = FOREACH raw GENERATE event_stop_time-event_start_time as dur, event_end_reason as fault; |
---|
11 | mapping = FOREACH duration GENERATE flatten(RealLabels(dur, fault)) as key, 1 as value; |
---|
12 | --filteredMapping = FILTER mapping BY key!=NULL; |
---|
13 | |
---|
14 | |
---|
15 | -- group and average |
---|
16 | grup = GROUP mapping BY key; |
---|
17 | rez = FOREACH grup GENERATE group, SUM(mapping.value) as sum; |
---|
18 | filteredRez = FILTER rez BY sum > 1000; |
---|
19 | |
---|
20 | STORE filteredRez INTO 'failurecause.rez' USING PigStorage(); |
---|
Note: See
TracBrowser
for help on using the repository browser.