zzcclp commented on a change in pull request #1618:
URL: https://github.com/apache/kylin/pull/1618#discussion_r604232697
##########
File path:
kylin-spark-project/kylin-spark-engine/src/main/scala/org/apache/kylin/engine/spark/builder/CubeTableEncoder.scala
##########
@@ -43,11 +43,15 @@ object CubeTableEncoder extends Logging {
val bucketThreshold = seg.kylinconf.getGlobalDictV2ThresholdBucketSize
val minBucketSize: Long = sourceCnt / bucketThreshold
+ var repartitionSizeAfterEncode = 0;
cols.asScala.foreach(
ref => {
val globalDict = new NGlobalDictionary(seg.project,
ref.tableAliasName, ref.columnName, seg.kylinconf.getHdfsWorkingDirectory)
val bucketSize =
globalDict.getBucketSizeOrDefault(seg.kylinconf.getGlobalDictV2MinHashPartitions)
val enlargedBucketSize = (((minBucketSize / bucketSize) + 1) *
bucketSize).toInt
+ if(enlargedBucketSize > repartitionSizeAfterEncode){
Review comment:
add a blank space before '(' and '{'
--
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]
