Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/15923#discussion_r94358078
--- Diff:
core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
---
@@ -305,40 +316,84 @@ final class ShuffleBlockFetcherIterator(
*/
override def next(): (BlockId, InputStream) = {
numBlocksProcessed += 1
- val startFetchWait = System.currentTimeMillis()
- currentResult = results.take()
- val result = currentResult
- val stopFetchWait = System.currentTimeMillis()
- shuffleMetrics.incFetchWaitTime(stopFetchWait - startFetchWait)
-
- result match {
- case SuccessFetchResult(_, address, size, buf, isNetworkReqDone) =>
- if (address != blockManager.blockManagerId) {
- shuffleMetrics.incRemoteBytesRead(buf.size)
- shuffleMetrics.incRemoteBlocksFetched(1)
- }
- bytesInFlight -= size
- if (isNetworkReqDone) {
- reqsInFlight -= 1
- logDebug("Number of requests in flight " + reqsInFlight)
- }
- case _ =>
- }
- // Send fetch requests up to maxBytesInFlight
- fetchUpToMaxBytes()
- result match {
- case FailureFetchResult(blockId, address, e) =>
- throwFetchFailedException(blockId, address, e)
+ var result: FetchResult = null
+ var input: InputStream = null
+ // Take the next fetched result and try to decompress it to detect
data corruption,
+ // then fetch it one more time if it's corrupt, throw
FailureFetchResult if the second fetch
--- End diff --
@Tagar Spark doesn't use Netty's Snappy compression.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
