Github user jackylk commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1144#discussion_r126050294
--- Diff:
integration/spark-common/src/main/scala/org/apache/carbondata/spark/rdd/CarbonGlobalDictionaryRDD.scala
---
@@ -375,90 +372,72 @@ class CarbonGlobalDictionaryGenerateRDD(
val distinctValueList = rddIter.next()._2
valuesBuffer ++= distinctValueList.values
rowCount += distinctValueList.rowCount
- // check high cardinality
- if (model.isFirstLoad && model.highCardIdentifyEnable
- && !model.isComplexes(split.index)
- && model.primDimensions(split.index).isColumnar) {
- isHighCardinalityColumn =
GlobalDictionaryUtil.isHighCardinalityColumn(
- valuesBuffer.size, model)
- if (isHighCardinalityColumn) {
- break
- }
- }
}
}
val combineListTime = System.currentTimeMillis() - t1
- if (isHighCardinalityColumn) {
- LOGGER.info(s"column ${ model.table.getTableUniqueName }." +
- s"${
- model.primDimensions(split.index)
- .getColName
- } is high cardinality column")
+ isDictionaryLocked = dictLock.lockWithRetries()
+ if (isDictionaryLocked) {
+ logInfo(s"Successfully able to get the dictionary lock for ${
+ model.primDimensions(split.index).getColName
+ }")
} else {
- isDictionaryLocked = dictLock.lockWithRetries()
- if (isDictionaryLocked) {
- logInfo(s"Successfully able to get the dictionary lock for ${
+ sys
+ .error(s"Dictionary file ${
--- End diff --
should use log only
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
