diff options
Diffstat (limited to 'sql')
-rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala | 5 | ||||
-rw-r--r-- | sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala | 5 |
2 files changed, 2 insertions, 8 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala index f5487740d3..28cd17fde4 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala @@ -301,12 +301,9 @@ case class InsertIntoParquetTable( } def writeShard(context: TaskContext, iter: Iterator[Row]): Int = { - // Hadoop wants a 32-bit task attempt ID, so if ours is bigger than Int.MaxValue, roll it - // around by taking a mod. We expect that no task will be attempted 2 billion times. - val attemptNumber = (context.attemptId % Int.MaxValue).toInt /* "reduce task" <split #> <attempt # = spark task #> */ val attemptId = newTaskAttemptID(jobtrackerID, stageId, isMap = false, context.partitionId, - attemptNumber) + context.attemptNumber) val hadoopContext = newTaskAttemptContext(wrappedConf.value, attemptId) val format = new AppendingParquetOutputFormat(taskIdOffset) val committer = format.getOutputCommitter(hadoopContext) diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala index ca0ec15139..42bc8a0b67 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala @@ -100,10 +100,7 @@ case class InsertIntoHiveTable( val wrappers = fieldOIs.map(wrapperFor) val outputData = new Array[Any](fieldOIs.length) - // Hadoop wants a 32-bit task attempt ID, so if ours is bigger than Int.MaxValue, roll it - // around by taking a mod. We expect that no task will be attempted 2 billion times. - val attemptNumber = (context.attemptId % Int.MaxValue).toInt - writerContainer.executorSideSetup(context.stageId, context.partitionId, attemptNumber) + writerContainer.executorSideSetup(context.stageId, context.partitionId, context.attemptNumber) iterator.foreach { row => var i = 0 |