Ngone51 commented on a change in pull request #28708:
URL: https://github.com/apache/spark/pull/28708#discussion_r454916426
##########
File path: core/src/test/scala/org/apache/spark/storage/BlockManagerSuite.scala
##########
@@ -1866,13 +1903,57 @@ class BlockManagerSuite extends SparkFunSuite with
Matchers with BeforeAndAfterE
assert(master.getLocations(blockIdLarge) === Seq(store1.blockManagerId))
assert(master.getLocations(blockIdSmall) === Seq(store1.blockManagerId))
- store1.decommissionRddCacheBlocks()
+ val decomManager = new BlockManagerDecommissioner(conf, store1)
+ decomManager.decommissionRddCacheBlocks()
// Smaller block offloaded to store2
assert(master.getLocations(blockIdSmall) === Seq(store2.blockManagerId))
// Larger block still present in store1 as it can't be offloaded
assert(master.getLocations(blockIdLarge) === Seq(store1.blockManagerId))
}
+ test("test migration of shuffle blocks during decommissioning") {
+ val shuffleManager1 = makeSortShuffleManager()
+ val bm1 = makeBlockManager(3500, "exec1", shuffleManager = shuffleManager1)
+ shuffleManager1.shuffleBlockResolver._blockManager = bm1
+
+ val shuffleManager2 = makeSortShuffleManager()
+ val bm2 = makeBlockManager(3500, "exec2", shuffleManager = shuffleManager2)
+ shuffleManager2.shuffleBlockResolver._blockManager = bm2
+
+ val blockSize = 5
+ val shuffleDataBlockContent = Array[Byte](0, 1, 2, 3, 4)
+ val shuffleData = ShuffleDataBlockId(0, 0, 0)
+ Files.write(bm1.diskBlockManager.getFile(shuffleData).toPath(),
shuffleDataBlockContent)
+ val shuffleIndexBlockContent = Array[Byte](5, 6, 7, 8, 9)
+ val shuffleIndex = ShuffleIndexBlockId(0, 0, 0)
+ Files.write(bm1.diskBlockManager.getFile(shuffleIndex).toPath(),
shuffleIndexBlockContent)
+
+ mapOutputTracker.registerShuffle(0, 1)
+ val decomManager = new BlockManagerDecommissioner(conf, bm1)
+ try {
+ mapOutputTracker.registerMapOutput(0, 0, MapStatus(bm1.blockManagerId,
Array(blockSize), 0))
+ assert(mapOutputTracker.shuffleStatuses(0).mapStatuses(0).location ===
bm1.blockManagerId)
+
+ val env = mock(classOf[SparkEnv])
+ when(env.conf).thenReturn(conf)
+ SparkEnv.set(env)
+
+ decomManager.refreshOffloadingShuffleBlocks()
+
+ eventually(timeout(1.second), interval(10.milliseconds)) {
+ assert(mapOutputTracker.shuffleStatuses(0).mapStatuses(0).location ===
bm2.blockManagerId)
Review comment:
Maybe it's better to remove shuffle data in `bm1` before checking `bm2`?
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
