mirror of https://github.com/apache/druid.git
87 lines
2.3 KiB
JSON
87 lines
2.3 KiB
JSON
{
|
|
"type": "index_hadoop",
|
|
"spec": {
|
|
"ioConfig": {
|
|
"type": "hadoop",
|
|
"inputSpec": {
|
|
"type": "static",
|
|
"inputFormat": "%s",
|
|
"paths": "example/compat/parquet-1217.parquet"
|
|
},
|
|
"metadataUpdateSpec": {
|
|
"type": "postgresql",
|
|
"connectURI": "jdbc:postgresql://localhost/druid",
|
|
"user": "druid",
|
|
"password": "asdf",
|
|
"segmentTable": "druid_segments"
|
|
},
|
|
"segmentOutputPath": "/tmp/segments"
|
|
},
|
|
"dataSchema": {
|
|
"dataSource": "test",
|
|
"parser": {
|
|
"type": "%s",
|
|
"parseSpec": {
|
|
"format": "%s",
|
|
"flattenSpec": {
|
|
"useFieldDiscovery": true,
|
|
"fields": [
|
|
{
|
|
"type": "root",
|
|
"name": "col"
|
|
},
|
|
{
|
|
"type": "path",
|
|
"name": "metric1",
|
|
"expr": "$.col"
|
|
}
|
|
]
|
|
},
|
|
"timestampSpec": {
|
|
"column": "timestamp",
|
|
"format": "auto",
|
|
"missingValue": "2018-09-01T00:00:00.000Z"
|
|
},
|
|
"dimensionsSpec": {
|
|
"dimensions": [],
|
|
"dimensionExclusions": [],
|
|
"spatialDimensions": []
|
|
}
|
|
}
|
|
},
|
|
"metricsSpec": [
|
|
{
|
|
"type": "count",
|
|
"name": "count"
|
|
},
|
|
{
|
|
"type": "longSum",
|
|
"name": "metric1",
|
|
"fieldName": "metric1"
|
|
}
|
|
],
|
|
"granularitySpec": {
|
|
"type": "uniform",
|
|
"segmentGranularity": "DAY",
|
|
"queryGranularity": "NONE",
|
|
"intervals": [
|
|
"2018-08-30/2020-09-02"
|
|
]
|
|
}
|
|
},
|
|
"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
|
|
}
|
|
}
|
|
}
|