venkata91 commented on a change in pull request #26339:
[SPARK-27194][SPARK-29302][SQL] Fix the issue that for dynamic partition
overwrite a task would conflict with its speculative task
URL: https://github.com/apache/spark/pull/26339#discussion_r403841559
##########
File path:
core/src/main/scala/org/apache/spark/internal/io/HadoopMapReduceCommitProtocol.scala
##########
@@ -91,6 +91,31 @@ class HadoopMapReduceCommitProtocol(
*/
private def stagingDir = new Path(path, ".spark-staging-" + jobId)
+ /**
+ * Get staging path for a task with dynamicPartitionOverwrite=true.
+ */
+ private def dynamicStagingTaskPath(dir: Option[String], taskContext:
TaskAttemptContext): Path = {
+ assert(dynamicPartitionOverwrite && dir.isDefined)
+ val attemptID = taskContext.getTaskAttemptID.getId
+ new Path(stagingDir, s"${dir.get}-${attemptID}")
+ }
+
+ /**
+ * Tracks the staging task files with dynamicPartitionOverwrite=true.
+ */
+ @transient private var dynamicStagingTaskFiles: mutable.Set[Path] = null
+
+ /**
+ * Get responding partition path for a task with
dynamicPartitionOverwrite=true.
+ */
+ private def getDynamicPartitionPath(stagingTaskFile: Path, context:
TaskAttemptContext): Path = {
+ assert(dynamicPartitionOverwrite)
Review comment:
Same here, do we need assert?
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
