Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/11498#discussion_r57097978
--- Diff:
core/src/main/scala/org/apache/spark/storage/disk/DiskBlockObjectWriter.scala
---
@@ -0,0 +1,132 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.storage.disk
+
+import java.io.File
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.serializer.{SerializationStream,
SerializerInstance}
+import org.apache.spark.storage.BlockId
+import org.apache.spark.util.Utils
+
+/**
+ * A class for writing JVM objects directly to a file on disk. This class
allows data to be appended
+ * to an existing block and can guarantee atomicity in the case of faults
as it allows the caller to
+ * revert partial writes.
+ *
+ * This class does not support concurrent writes. Also, once the writer
has been opened it cannot be
+ * reopened again.
+ */
+private[spark] class DiskBlockObjectWriter(
+ private[this] var diskBlockWriter: DiskBlockWriter,
+ serializerInstance: SerializerInstance,
+ val blockId: BlockId = null)
+ extends Logging {
+
+ private var objOut: SerializationStream = null
+ private var initialized = false
+ private var hasBeenClosed = false
+ private var commitAndCloseHasBeenCalled = false
+
+ def file: File = diskBlockWriter.file
+
+ def open(): DiskBlockObjectWriter = {
+ if (hasBeenClosed) {
+ throw new IllegalStateException("Writer already closed. Cannot be
reopened.")
+ }
+ diskBlockWriter.open()
+ objOut = serializerInstance.serializeStream(diskBlockWriter)
+ initialized = true
+ this
+ }
+
+ def close() {
+ Utils.tryWithSafeFinally {
+ if (initialized) {
+ if (diskBlockWriter.syncWrites) {
+ objOut.flush()
+ }
+ }
+ } {
+ if (initialized) {
+ objOut.close()
+ }
+ diskBlockWriter = null
+ objOut = null
+ initialized = false
+ hasBeenClosed = true
+ }
+ }
+
+ /**
+ * Flush the partial writes and commit them as a single atomic block.
+ */
+ def commitAndClose(): Unit = {
+ if (initialized) {
+ objOut.flush()
--- End diff --
Note that we don't explicitly close `objOut` here. Neither did the old
code, which is why I preserved that behavior after the split.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
