Github user techaddict commented on a diff in the pull request: https://github.com/apache/spark/pull/11105#discussion_r73330741 --- Diff: core/src/main/scala/org/apache/spark/executor/TaskMetrics.scala --- @@ -220,8 +220,27 @@ class TaskMetrics private[spark] () extends Serializable { */ @transient private[spark] lazy val externalAccums = new ArrayBuffer[AccumulatorV2[_, _]] + /** + * All data property accumulators registered with this task. + */ + @transient private lazy val dataPropertyAccums = new ArrayBuffer[AccumulatorV2[_, _]] + private[spark] def registerAccumulator(a: AccumulatorV2[_, _]): Unit = { externalAccums += a + if (a.dataProperty) { + dataPropertyAccums += a + } + } + + private[spark] def hasDataPropertyAccumulators(): Boolean = { + !dataPropertyAccums.isEmpty + } + + /** + * Mark an rdd/shuffle/and partition as fully processed for all dataProperty accumulators. + */ + private[spark] def markFullyProcessed(rddId: Int, shuffleWriteId: Int, partitionId: Int) = { + dataPropertyAccums.map(_.markFullyProcessed(rddId, shuffleWriteId, partitionId)) --- End diff -- should be `foreach` instead of `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. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org