Github user jackylk commented on a diff in the pull request:
https://github.com/apache/incubator-carbondata/pull/203#discussion_r80922605
--- Diff:
integration/spark/src/main/scala/org/apache/carbondata/spark/rdd/CarbonDataLoadRDD.scala
---
@@ -462,3 +478,133 @@ class CarbonDataLoadRDD[K, V](
}
}
+class CarbonRDDDataLoadRDD[K, V](
+ sc: SparkContext,
+ result: DataLoadResult[K, V],
+ carbonLoadModel: CarbonLoadModel,
+ var storeLocation: String,
+ hdfsStoreLocation: String,
+ kettleHomePath: String,
+ columinar: Boolean,
+ loadCount: Integer,
+ tableCreationTime: Long,
+ schemaLastUpdatedTime: Long,
+ prev: RDD[Row])
+ extends RDD[(K, V)](prev)
+ with Logging {
+
+ sc.setLocalProperty("spark.scheduler.pool", "DDL")
+
+ @DeveloperApi
+ override def compute(theSplit: Partition, context: TaskContext):
Iterator[(K, V)] = {
+ val LOGGER = LogServiceFactory.getLogService(this.getClass.getName)
+ val resultIter = new Iterator[(K, V)] {
+ var partitionID = "0"
+ val loadMetadataDetails = new LoadMetadataDetails()
+ var uniqueLoadStatusId = carbonLoadModel.getTableName +
CarbonCommonConstants.UNDERSCORE +
+ theSplit.index
+ try {
+ loadMetadataDetails.setPartitionCount(partitionID)
+
loadMetadataDetails.setLoadStatus(CarbonCommonConstants.STORE_LOADSTATUS_FAILURE)
+ carbonLoadModel.setPartitionId(partitionID)
+ carbonLoadModel.setSegmentId(String.valueOf(loadCount))
+ carbonLoadModel.setTaskNo(String.valueOf(theSplit.index))
+
+ storeLocation = CarbonDataLoadRDD.initialize(carbonLoadModel,
theSplit.index)
+
loadMetadataDetails.setLoadStatus(CarbonCommonConstants.STORE_LOADSTATUS_SUCCESS)
+ val rddIteratorKey = UUID.randomUUID().toString
+ try{
+ RddInputUtils.put(rddIteratorKey,
+ new RddIterator(firstParent[Row].iterator(theSplit, context),
carbonLoadModel))
+ carbonLoadModel.setRddIteratorKey(rddIteratorKey)
--- End diff --
Why can't you just set the iterator object itself in the carbonLoadModel
instead of putting it in a global map?
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
