segmentGenerationJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentGenerationJobRunner'
segmentTarPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentTarPushJobRunner'
segmentUriPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentUriPushJobRunner'
segmentMetadataPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentMetadataPushJobRunner'
stagingDir: hdfs://examples/batch/airlineStats/staging
# Recommended to set jobType to SegmentCreationAndMetadataPush for production environments where Pinot Deep Store is configured
jobType: SegmentCreationAndTarPush
inputDirURI: 'examples/batch/airlineStats/rawdata'
includeFileNamePattern: 'glob:**/*.avro'
outputDirURI: 'hdfs:///examples/batch/airlineStats/segments'
className: org.apache.pinot.plugin.filesystem.HadoopPinotFS
className: org.apache.pinot.spi.filesystem.LocalPinotFS
className: 'org.apache.pinot.plugin.inputformat.avro.AvroRecordReader'
tableName: 'airlineStats'
schemaURI: 'http://localhost:9000/tables/airlineStats/schema'
tableConfigURI: 'http://localhost:9000/tables/airlineStats'
segmentNameGeneratorSpec:
segment.name.prefix: 'airlineStats_batch'
exclude.sequence.id: true
- controllerURI: 'http://localhost:9000'
pushRetryIntervalMillis: 1000