srowen commented on a change in pull request #34980:
URL: https://github.com/apache/spark/pull/34980#discussion_r779092355
##########
File path: core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala
##########
@@ -2123,6 +2125,80 @@ class BlockManagerSuite extends SparkFunSuite with
Matchers with BeforeAndAfterE
store.putSingle(broadcast0BlockId, a, StorageLevel.DISK_ONLY)
}
+ test("check KryoException when getting disk blocks and 'Input/output error'
is occurred") {
+ val kyoSerializerWithDiskCorruptedInputStream
Review comment:
Total nit: kyo
##########
File path: core/src/main/scala/org/apache/spark/storage/BlockManager.scala
##########
@@ -926,30 +933,47 @@ private[spark] class BlockManager(
})
Some(new BlockResult(ci, DataReadMethod.Memory, info.size))
} else if (level.useDisk && diskStore.contains(blockId)) {
- val diskData = diskStore.getBytes(blockId)
- val iterToReturn: Iterator[Any] = {
- if (level.deserialized) {
- val diskValues = serializerManager.dataDeserializeStream(
- blockId,
- diskData.toInputStream())(info.classTag)
- maybeCacheDiskValuesInMemory(info, blockId, level, diskValues)
- } else {
- val stream = maybeCacheDiskBytesInMemory(info, blockId, level,
diskData)
- .map { _.toInputStream(dispose = false) }
- .getOrElse { diskData.toInputStream() }
- serializerManager.dataDeserializeStream(blockId,
stream)(info.classTag)
+ try {
+ val diskData = diskStore.getBytes(blockId)
+ val iterToReturn: Iterator[Any] = {
+ if (level.deserialized) {
+ val diskValues = serializerManager.dataDeserializeStream(
+ blockId,
+ diskData.toInputStream())(info.classTag)
+ maybeCacheDiskValuesInMemory(info, blockId, level, diskValues)
+ } else {
+ val stream = maybeCacheDiskBytesInMemory(info, blockId, level,
diskData)
+ .map { _.toInputStream(dispose = false) }
+ .getOrElse { diskData.toInputStream() }
+ serializerManager.dataDeserializeStream(blockId,
stream)(info.classTag)
+ }
}
+ val ci = CompletionIterator[Any, Iterator[Any]](iterToReturn, {
+ releaseLockAndDispose(blockId, diskData, taskContext)
+ })
+ Some(new BlockResult(ci, DataReadMethod.Disk, info.size))
+ } catch {
+ case ex: KryoException if ex.getCause.isInstanceOf[IOException] =>
+ // We need to have clear error message to catch environmental
problems easily.
+ // Further details:
https://issues.apache.org/jira/browse/SPARK-37710
+ processKryoException(ex, blockId)
+ throw ex
}
- val ci = CompletionIterator[Any, Iterator[Any]](iterToReturn, {
- releaseLockAndDispose(blockId, diskData, taskContext)
- })
- Some(new BlockResult(ci, DataReadMethod.Disk, info.size))
} else {
handleLocalReadFailure(blockId)
}
}
}
+ private def processKryoException(ex: KryoException, blockId: BlockId): Unit
= {
+ var warningMessage = s"${ex.getMessage}. ${blockManagerId.toString} -
blockName: $blockId"
+ val file = diskBlockManager.getFile(blockId)
+ if (file.exists()) {
+ warningMessage = warningMessage + s" - blockDiskPath:
${file.getAbsolutePath}"
Review comment:
Total nit: warningMessage can be in the format string
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
