rubenssoto commented on issue #1902: URL: https://github.com/apache/hudi/issues/1902#issuecomment-672306115
Thank you so much for your help, it worked. Last question, Hudi organized data very well by files, but created some small files, is there any way to solve? <img width="1680" alt="Captura de Tela 2020-08-11 às 19 01 56" src="https://user-images.githubusercontent.com/36298331/89953414-6bd09380-dc05-11ea-8fe9-8167ac6a91b9.png"> { "hoodie.datasource.write.recordkey.field":"created_date_brt,id", "hoodie.datasource.write.table.name":"order", "hoodie.datasource.write.operation":"bulk_insert", "hoodie.datasource.write.partitionpath.field":"partitionpath", "hoodie.datasource.write.hive_style_partitioning":"true", "hoodie.combine.before.insert":"true", "hoodie.combine.before.upsert":"false", "hoodie.datasource.write.precombine.field":"LineCreatedTimestamp", "hoodie.datasource.write.keygenerator.class":"org.apache.hudi.keygen.ComplexKeyGenerator", "hoodie.parquet.small.file.limit":943718400, "hoodie.parquet.max.file.size":1073741824, "hoodie.parquet.block.size":1073741824, "hoodie.copyonwrite.record.size.estimate":512, "hoodie.cleaner.commits.retained":5, "hoodie.datasource.hive_sync.enable":"true", "hoodie.datasource.hive_sync.database":"datalake_raw", "hoodie.datasource.hive_sync.table":"order", "hoodie.datasource.hive_sync.partition_fields":"partitionpath", "hoodie.datasource.hive_sync.partition_extractor_class":"org.apache.hudi.hive.MultiPartKeysValueExtractor", "hoodie.datasource.hive_sync.jdbcurl":"jdbc:hive2://ip-10-0-82-196.us-west-2.compute.internal:1000", "hoodie.insert.shuffle.parallelism":1500, "hoodie.bulkinsert.shuffle.parallelism":8, "hoodie.upsert.shuffle.parallelism":1500 } ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
