vanzin commented on a change in pull request #25299: [SPARK-27651][Core] Avoid
the network when shuffle blocks are fetched from the same host
URL: https://github.com/apache/spark/pull/25299#discussion_r348105943
##########
File path:
core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -121,37 +177,88 @@ class ShuffleBlockFetcherIteratorSuite extends
SparkFunSuite with PrivateMethodT
false)
// 3 local blocks fetched in initialization
- verify(blockManager, times(3)).getBlockData(any())
+ verify(blockManager, times(3)).getLocalBlockData(any())
- for (i <- 0 until 5) {
- assert(iterator.hasNext, s"iterator should have 5 elements but actually
has $i elements")
+ val allBlocks = localBlocks ++ remoteBlocks ++ hostLocalBlocks
+ for (i <- 0 until allBlocks.size) {
+ assert(iterator.hasNext,
+ s"iterator should have ${allBlocks.size} elements but actually has $i
elements")
val (blockId, inputStream) = iterator.next()
// Make sure we release buffers when a wrapped input stream is closed.
- val mockBuf = localBlocks.getOrElse(blockId, remoteBlocks(blockId))
- // Note: ShuffleBlockFetcherIterator wraps input streams in a
BufferReleasingInputStream
- val wrappedInputStream =
inputStream.asInstanceOf[BufferReleasingInputStream]
- verify(mockBuf, times(0)).release()
- val delegateAccess = PrivateMethod[InputStream](Symbol("delegate"))
-
- verify(wrappedInputStream.invokePrivate(delegateAccess()),
times(0)).close()
- wrappedInputStream.close()
- verify(mockBuf, times(1)).release()
- verify(wrappedInputStream.invokePrivate(delegateAccess()),
times(1)).close()
- wrappedInputStream.close() // close should be idempotent
- verify(mockBuf, times(1)).release()
- verify(wrappedInputStream.invokePrivate(delegateAccess()),
times(1)).close()
+ val mockBuf = allBlocks(blockId)
+ verifyBufferRelease(mockBuf, inputStream)
}
- // 3 local blocks, and 2 remote blocks
- // (but from the same block manager so one call to fetchBlocks)
- verify(blockManager, times(3)).getBlockData(any())
+ // 4 host-local locks fetched
+ verify(blockManager, times(4))
+ .getHostLocalShuffleData(any(), meq(Array("local-dir")))
+
+ // 2 remote blocks are read from the same block manager
verify(transfer, times(1)).fetchBlocks(any(), any(), any(), any(), any(),
any())
+ assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size
=== 1)
}
- test("fetch continuous blocks in batch successful 3 local reads + 2 remote
reads") {
+ test("error during accessing host local dirs for executors") {
val blockManager = mock(classOf[BlockManager])
- val localBmId = BlockManagerId("test-client", "test-client", 1)
+ val localBmId = BlockManagerId("test-local-client", "test-local-host", 1)
+ doReturn(localBmId).when(blockManager).blockManagerId
+ val hostLocalBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockId(0, 1, 0) -> createMockManagedBuffer())
+
+ hostLocalBlocks.foreach { case (blockId, buf) =>
+ doReturn(buf)
+ .when(blockManager)
+ .getHostLocalShuffleData(meq(blockId.asInstanceOf[ShuffleBlockId]),
any())
+ }
+ val hostLocalBmId = BlockManagerId("test-host-local-client-1",
"test-local-host", 3)
+
+ val mockExternalBlockStoreClient = mock(classOf[ExternalBlockStoreClient])
+ val hostLocalDirManager = new HostLocalDirManager(
+ futureExecutionContext = global,
+ cacheSize = 1,
+ externalBlockStoreClient = mockExternalBlockStoreClient,
+ host = "localhost",
+ externalShuffleServicePort = 7337)
+
+
when(blockManager.hostLocalDirManager).thenReturn(Some(hostLocalDirManager))
+ when(mockExternalBlockStoreClient.getHostLocalDirs(any(), any(), any(),
any()))
+ .thenAnswer((invocation: InvocationOnMock) => {
+ val completableFuture = invocation.getArguments()(3)
+ .asInstanceOf[CompletableFuture[java.util.Map[String,
Array[String]]]]
+ Future {
Review comment:
?
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
