Skip to content

[SPARK-56028][CORE] Fix shuffle block GC not cleanup checksum file #54857

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
CavemanIV wants to merge 2 commits into
base: master
Choose a base branch
from
+6 −3
Open

[SPARK-56028][CORE] Fix shuffle block GC not cleanup checksum file #54857

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
969633b
fix shuffle GC not cleanup checksum file
CavemanIV Mar 17, 2026
eee273d
add checksum in existing UT
CavemanIV Mar 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion core/src/main/scala/org/apache/spark/shuffle/IndexShuffleBlockResolver.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -662,7 +662,8 @@ private[spark] class IndexShuffleBlockResolver(
override def getBlocksForShuffle(shuffleId: Int, mapId: Long): Seq[BlockId] = {
Seq(
ShuffleIndexBlockId(shuffleId, mapId, NOOP_REDUCE_ID),
ShuffleDataBlockId(shuffleId, mapId, NOOP_REDUCE_ID)
ShuffleDataBlockId(shuffleId, mapId, NOOP_REDUCE_ID),
ShuffleChecksumBlockId(shuffleId, mapId, NOOP_REDUCE_ID)
)
}

Expand Down
6 changes: 4 additions & 2 deletions core/src/test/scala/org/apache/spark/ExternalShuffleServiceSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ import org.apache.spark.network.TransportContext
import org.apache.spark.network.netty.SparkTransportConf
import org.apache.spark.network.server.TransportServer
import org.apache.spark.network.shuffle.{ExecutorDiskUtils, ExternalBlockHandler, ExternalBlockStoreClient}
import org.apache.spark.storage.{BroadcastBlockId, RDDBlockId, ShuffleBlockId, ShuffleDataBlockId, ShuffleIndexBlockId, StorageLevel}
import org.apache.spark.storage.{BroadcastBlockId, RDDBlockId, ShuffleBlockId, ShuffleChecksumBlockId, ShuffleDataBlockId, ShuffleIndexBlockId, StorageLevel}
import org.apache.spark.util.{ThreadUtils, Utils}
import org.apache.spark.util.io.ChunkedByteBuffer

Expand Down Expand Up @@ -270,6 +270,8 @@ class ExternalShuffleServiceSuite extends ShuffleSuite with Eventually {
ShuffleDataBlockId(shuffleBlockId.shuffleId, shuffleBlockId.mapId,
shuffleBlockId.reduceId).name,
ShuffleIndexBlockId(shuffleBlockId.shuffleId, shuffleBlockId.mapId,
shuffleBlockId.reduceId).name,
ShuffleChecksumBlockId(shuffleBlockId.shuffleId, shuffleBlockId.mapId,
shuffleBlockId.reduceId).name
).map { blockId =>
new File(ExecutorDiskUtils.getFilePath(dirs,
Expand All @@ -283,7 +285,7 @@ class ExternalShuffleServiceSuite extends ShuffleSuite with Eventually {
promise.future
}
val filesToCheck = promises.flatMap(p => ThreadUtils.awaitResult(p, Duration(2, "sec")))
assert(filesToCheck.length == 4)
assert(filesToCheck.length == 6)
assert(filesToCheck.forall(_.exists()))

if (enabled) {
Expand Down