ravipesala commented on a change in pull request #3182: [CARBONDATA-3343]
Compaction for Range Sort
URL: https://github.com/apache/carbondata/pull/3182#discussion_r280736136
##########
File path:
integration/spark-common/src/main/scala/org/apache/carbondata/spark/rdd/CarbonMergerRDD.scala
##########
@@ -589,9 +601,91 @@ class CarbonMergerRDD[K, V](
// Change string type to support all types
val sampleRdd = scanRdd
.map(row => (row.get(0, sparkDataType), null))
+ val sortedRdd = sampleRdd.sortBy(_._1, true)(objectOrdering,
classTag[AnyRef])
val value = new DataSkewRangePartitioner(
- defaultParallelism, sampleRdd, true)(objectOrdering, classTag[Object])
- CarbonCompactionUtil.getRangesFromVals(value.rangeBounds, value.minMaxVals)
+ defaultParallelism, sortedRdd, true)(objectOrdering, classTag[Object])
+ if(minVal == null && maxVal == null) {
+ CarbonCompactionUtil
+ .getRangesFromVals(value.rangeBounds, value.rangeBounds(0),
value.rangeBounds(1))
+ } else {
+ CarbonCompactionUtil.getRangesFromVals(value.rangeBounds, minVal, maxVal)
+ }
+ }
+
+ def getOverallMinMax(carbonInputSplits: mutable.Seq[CarbonInputSplit],
Review comment:
What is the use of getting overallminmax of to be compacted segments? what
is the issue if we use min/max getting from partitioner?
----------------------------------------------------------------
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]
With regards,
Apache Git Services
