akashrn5 commented on a change in pull request #3793:
URL: https://github.com/apache/carbondata/pull/3793#discussion_r442947011
##########
File path:
integration/spark/src/main/scala/org/apache/spark/sql/execution/command/mutation/merge/CarbonMergeDataSetCommand.scala
##########
@@ -269,11 +271,10 @@ case class CarbonMergeDataSetCommand(
new SparkCarbonFileFormat().prepareWrite(sparkSession, job,
Map(), schema)
val config = SparkSQLUtil.broadCastHadoopConf(sparkSession.sparkContext,
job.getConfiguration)
-
(frame.rdd.coalesce(DistributionUtil.getConfiguredExecutors(sparkSession.sparkContext)).
- mapPartitionsWithIndex { case (index, iter) =>
+ (frame.rdd.mapPartitionsWithIndex { case (index, iter) =>
CarbonProperties.getInstance().addProperty(CarbonLoadOptionConstants
.ENABLE_CARBON_LOAD_DIRECT_WRITE_TO_STORE_PATH, "true")
- val confB = config.value.value
+ val confB = new Configuration(config.value.value)
Review comment:
sorry, i did not understand conf is tampered, can you please tell what
type error you got during concurrent scenarios?
##########
File path:
integration/spark/src/test/scala/org/apache/carbondata/spark/testsuite/merge/MergeTestCase.scala
##########
@@ -702,10 +716,25 @@ class MergeTestCase extends QueryTest with
BeforeAndAfterAll {
insertExpr(insertMap).
whenMatched("B.deleted=true").
delete().execute()
+ assert(getDeleteDeltaFileCount("target") == 1)
checkAnswer(sql("select count(*) from target"), Seq(Row(3)))
checkAnswer(sql("select * from target order by key"), Seq(Row("c", "200"),
Row("d", "3"), Row("e", "100")))
}
+ private def getDeleteDeltaFileCount(tableName: String): Int = {
+ val table = CarbonEnv.getCarbonTable(None,
tableName)(sqlContext.sparkSession)
+ val path = table.getTablePath
Review comment:
yeah, saw that, but if we give the path till Part directory, we can
reduce the files in list, so better to change the path.
----------------------------------------------------------------
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]
