cloud-fan commented on a change in pull request #25620: [SPARK-25341][Core]
Support rolling back a shuffle map stage and re-generate the shuffle files
URL: https://github.com/apache/spark/pull/25620#discussion_r321766066
##########
File path: core/src/main/scala/org/apache/spark/scheduler/MapStatus.scala
##########
@@ -100,16 +108,19 @@ private[spark] object MapStatus {
*
* @param loc location where the task is being executed.
* @param compressedSizes size of the blocks, indexed by reduce partition id.
+ * @param mapTId unique task id for the task
*/
private[spark] class CompressedMapStatus(
private[this] var loc: BlockManagerId,
- private[this] var compressedSizes: Array[Byte])
+ private[this] var compressedSizes: Array[Byte],
+ private[this] var mapTId: Long)
extends MapStatus with Externalizable {
- protected def this() = this(null, null.asInstanceOf[Array[Byte]]) // For
deserialization only
+ // For deserialization only
+ protected def this() = this(null, null.asInstanceOf[Array[Byte]], -1)
- def this(loc: BlockManagerId, uncompressedSizes: Array[Long]) {
- this(loc, uncompressedSizes.map(MapStatus.compressSize))
+ def this(loc: BlockManagerId, uncompressedSizes: Array[Long], taskAttemptId:
Long) {
Review comment:
`mapTaskId`
----------------------------------------------------------------
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
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
