查询数据
初始化环境
source /opt/client/bigdata_env
source /opt/client/Hudi/component_env
启动客户端
spark-shell --master yarn --driver-memory 20g --driver-cores 4 --executor-memory 12g --executor-cores 4 --num-executors 50 --conf spark.executor.memoryOverhead=4096
导入包
import org.apache.hudi.QuickstartUtils._import scala.collection.JavaConversions._import org.apache.spark.sql.SaveMode._import org.apache.hudi.DataSourceReadOptions._import org.apache.hudi.DataSourceWriteOptions._import org.apache.hudi.config.HoodieWriteConfig._
查询
val org_reader = spark.read.format("org.apache.hudi").load("hdfs://hacluster/hudi/default/o_org")org_reader.registerTempTable("hudi_o_org")
spark.sql("select count(*) from hudi_o_org").show()
spark.sql("desc hudi_o_org").show(200,false)
