Indhumathi27 commented on a change in pull request #3584: [CARBONDATA-3718]
Support SegmentLevel MinMax for better Pruning and less driver memory usage for
cache
URL: https://github.com/apache/carbondata/pull/3584#discussion_r394837435
##########
File path:
integration/spark/src/main/scala/org/apache/carbondata/spark/rdd/InsertTaskCompletionListener.scala
##########
@@ -20,21 +20,32 @@ package org.apache.carbondata.spark.rdd
import org.apache.spark.TaskContext
import
org.apache.spark.sql.carbondata.execution.datasources.tasklisteners.CarbonLoadTaskCompletionListener
import org.apache.spark.sql.execution.command.ExecutionErrors
+import org.apache.spark.util.CollectionAccumulator
+import org.apache.carbondata.core.segmentmeta.SegmentMetaDataInfo
import org.apache.carbondata.core.util.{DataTypeUtil, ThreadLocalTaskInfo}
import org.apache.carbondata.processing.loading.{DataLoadExecutor,
FailureCauses}
import org.apache.carbondata.spark.util.CommonUtil
class InsertTaskCompletionListener(dataLoadExecutor: DataLoadExecutor,
- executorErrors: ExecutionErrors)
+ executorErrors: ExecutionErrors,
+ segmentMetaDataAccumulator: CollectionAccumulator[Map[String,
SegmentMetaDataInfo]],
+ tableName: String,
+ segmentId: String)
extends CarbonLoadTaskCompletionListener {
override def onTaskCompletion(context: TaskContext): Unit = {
try {
- dataLoadExecutor.close()
+ // fill segment level minMax to accumulator
+ CarbonDataRDDFactory.fillSegmentMetaDataInfoToAccumulator(tableName,
Review comment:
done
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
