dataset > cars.csv from kaggle data set (all_anonymized_2015_11_2017_03.csv)
logstash terminal
]$ bin/logstash -f /home/elk/data/logstash.config
[2018-03-22T17:48:18,821][INFO ][logstash.outputs.elasticsearch] Elasticsearch pool URLs updated {:changes=>{:removed=>, :added=>[http://localhost:9200/]}}
[2018-03-22T17:48:18,832][INFO ][logstash.outputs.elasticsearch] Running health check to see if an Elasticsearch connection is working {:healthcheck_url=>http://localhost:9200/, :path=>"/"}
[2018-03-22T17:48:19,049][WARN ][logstash.outputs.elasticsearch] Restored connection to ES instance {:url=>"http://localhost:9200/"}
[2018-03-22T17:48:19,118][INFO ][logstash.outputs.elasticsearch] ES Output version determined {:es_version=>6}
[2018-03-22T17:48:19,124][WARN ][logstash.outputs.elasticsearch] Detected a 6.x and above cluster: the type
event field won't be used to determine the document _type {:es_version=>6}
[2018-03-22T17:48:19,156][INFO ][logstash.outputs.elasticsearch] Using mapping template from {:path=>nil}
[2018-03-22T17:48:19,176][INFO ][logstash.outputs.elasticsearch] Attempting to install template {:manage_template=>{"template"=>"logstash-", "version"=>60001, "settings"=>{"index.refresh_interval"=>"5s"}, "mappings"=>{"default"=>{"dynamic_templates"=>[{"message_field"=>{"path_match"=>"message", "match_mapping_type"=>"string", "mapping"=>{"type"=>"text", "norms"=>false}}}, {"string_fields"=>{"match"=>"", "match_mapping_type"=>"string", "mapping"=>{"type"=>"text", "norms"=>false, "fields"=>{"keyword"=>{"type"=>"keyword", "ignore_above"=>256}}}}}], "properties"=>{"@timestamp"=>{"type"=>"date"}, "@version"=>{"type"=>"keyword"}, "geoip"=>{"dynamic"=>true, "properties"=>{"ip"=>{"type"=>"ip"}, "location"=>{"type"=>"geo_point"}, "latitude"=>{"type"=>"half_float"}, "longitude"=>{"type"=>"half_float"}}}}}}}}
[2018-03-22T17:48:19,224][INFO ][logstash.outputs.elasticsearch] New Elasticsearch output {:class=>"LogStash::Outputs::ElasticSearch", :hosts=>["//localhost"]}
[2018-03-22T17:48:19,837][INFO ][logstash.pipeline ] Pipeline started succesfully {:pipeline_id=>"main", :thread=>"#<Thread:0x2689c8f6 run>"}
[2018-03-22T17:48:19,979][INFO ][logstash.agent ] Pipelines running {:count=>1, :pipelines=>["main"]}
It got stuck here
logstash config
input {
file {
path => "/home/elk/data/cars.csv"
start_position => "beginning"
sincedb_path => "/dev/null"
}
}
filter {
csv {
separator => ","
columns => ["maker","model","mileage","manufacture_year","engine_displacement","engine_power","body_type","color_slug","stk_year","transmission","door_count","seat_count","fuel_type","date_created","date_last_seen","price_eur"]
}
mutate {convert => ["mileage","integer"]}
mutate {convert => ["price_eur","float"]}
mutate {convert => ["engine_power","integer"]}
mutate {convert => ["door_count","integer"]}
mutate {convert => ["seat_count","integer"]}
}
output {
elasticsearch {
hosts => "localhost"
index => "cars"
document_type => "sold_cars"
}
stdout {}
}
http://localhost:9200/_cat/indices?v
health status index uuid pri rep docs.count docs.deleted store.size pri.store.size
For testing I have manually POST test/doc and working fine.
Can anyone help on this