mirror of https://github.com/apache/druid.git
76 lines
2.1 KiB
JSON
76 lines
2.1 KiB
JSON
|
{
|
||
|
|
"type": "index_hadoop",
|
||
|
|
"spec": {
|
||
|
|
"ioConfig": {
|
||
|
|
"type": "hadoop",
|
||
|
|
"inputSpec": {
|
||
|
|
"type": "static",
|
||
|
|
"inputFormat": "io.druid.data.input.parquet.DruidParquetInputFormat",
|
||
|
|
"paths": "wikipedia.gz.parquet"
|
||
|
|
},
|
||
|
|
"metadataUpdateSpec": {
|
||
|
|
"type": "postgresql",
|
||
|
|
"connectURI": "jdbc:postgresql://localhost/druid",
|
||
|
|
"user" : "druid",
|
||
|
|
"password" : "asdf",
|
||
|
|
"segmentTable": "druid_segments"
|
||
|
|
},
|
||
|
|
"segmentOutputPath": "/tmp/segments"
|
||
|
|
},
|
||
|
|
"dataSchema": {
|
||
|
|
"dataSource": "wikipedia",
|
||
|
|
"parser": {
|
||
|
|
"type": "parquet",
|
||
|
|
"parseSpec": {
|
||
|
|
"format": "timeAndDims",
|
||
|
|
"timestampSpec": {
|
||
|
|
"column": "timestamp",
|
||
|
|
"format": "auto"
|
||
|
|
},
|
||
|
|
"dimensionsSpec": {
|
||
|
|
"dimensions": [
|
||
|
|
"page",
|
||
|
|
"language",
|
||
|
|
"user",
|
||
|
|
"unpatrolled"
|
||
|
|
],
|
||
|
|
"dimensionExclusions": [],
|
||
|
|
"spatialDimensions": []
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"metricsSpec": [{
|
||
|
|
"type": "count",
|
||
|
|
"name": "count"
|
||
|
|
}, {
|
||
|
|
"type": "doubleSum",
|
||
|
|
"name": "deleted",
|
||
|
|
"fieldName": "deleted"
|
||
|
|
}, {
|
||
|
|
"type": "doubleSum",
|
||
|
|
"name": "delta",
|
||
|
|
"fieldName": "delta"
|
||
|
|
}],
|
||
|
|
"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
|
||
|
|
}
|
||
|
|
}
|
||
|
|
}
|