druid/extensions-contrib/parquet-extensions/example/impala_hadoop_parquet_job.json

66 lines
1.9 KiB
JSON

{
"type": "index_hadoop",
"spec": {
"ioConfig": {
"type": "hadoop",
"inputSpec": {
"type": "static",
"inputFormat": "io.druid.data.input.parquet.DruidParquetInputFormat",
"paths": "example/284a0e001476716b-56d5676f53bd6e85_115466471_data.0.parq"
},
"metadataUpdateSpec": {
"type": "postgresql",
"connectURI": "jdbc:postgresql://localhost/druid",
"user" : "druid",
"password" : "asdf",
"segmentTable": "druid_segments"
},
"segmentOutputPath": "/tmp/segments"
},
"dataSchema": {
"dataSource": "impala",
"parser": {
"type": "parquet",
"binaryAsString": true,
"parseSpec": {
"format": "timeAndDims",
"timestampSpec": {
"column": "ts",
"format": "auto"
},
"dimensionsSpec": {
"dimensions": [
"field"
],
"dimensionExclusions": [],
"spatialDimensions": []
}
}
},
"metricsSpec": [{
"type": "count",
"name": "count"
}],
"granularitySpec": {
"type": "uniform",
"segmentGranularity": "DAY",
"queryGranularity": "NONE",
"intervals": ["2013-08-30/2013-09-02"]
}
},
"tuningConfig": {
"type": "hadoop",
"workingPath": "tmp/working_path",
"partitionsSpec": {
"targetPartitionSize": 5000000
},
"jobProperties" : {
"mapreduce.map.java.opts": "-server -Duser.timezone=UTC -Dfile.encoding=UTF-8 -XX:+PrintGCDetails -XX:+PrintGCTimeStamps",
"mapreduce.reduce.java.opts": "-server -Duser.timezone=UTC -Dfile.encoding=UTF-8 -XX:+PrintGCDetails -XX:+PrintGCTimeStamps",
"mapred.child.java.opts": "-server -XX:+PrintGCDetails -XX:+PrintGCTimeStamps"
},
"leaveIntermediate": true
}
}
}