Github user brkyvz commented on a diff in the pull request:
https://github.com/apache/spark/pull/9421#discussion_r44086994
--- Diff:
extras/kinesis-asl/src/main/scala/org/apache/spark/streaming/kinesis/KinesisCheckpointer.scala
---
@@ -0,0 +1,117 @@
+/*
+ * 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.streaming.kinesis
+
+import java.util.concurrent._
+
+import scala.util.control.NonFatal
+
+import
com.amazonaws.services.kinesis.clientlibrary.interfaces.IRecordProcessorCheckpointer
+import com.amazonaws.services.kinesis.clientlibrary.types.ShutdownReason
+
+import org.apache.spark.Logging
+import org.apache.spark.streaming.Duration
+import org.apache.spark.util.ThreadUtils
+
+/**
+ * This is a helper class for managing Kinesis checkpointing.
+ *
+ * @param receiver The receiver that keeps track of which sequence numbers
we can checkpoint
+ * @param checkpointInterval How frequently we will checkpoint to DynamoDB
+ * @param workerId Worker Id of KCL worker for logging purposes
+ */
+private[kinesis] class KinesisCheckpointer(
+ receiver: KinesisReceiver[_],
+ checkpointInterval: Duration,
+ workerId: String) extends Logging {
+
+ // a map from shardId's to checkpointers
+ private val checkpointers = new ConcurrentHashMap[String,
IRecordProcessorCheckpointer]()
+
+ private val lastCheckpointedSeqNums = new ConcurrentHashMap[String,
String]()
+
+ private val checkpointerThread = startCheckpointerThread()
+
+ /** Update the checkpointer instance to the most recent one for the
given shardId. */
+ def setCheckpointer(shardId: String, checkpointer:
IRecordProcessorCheckpointer): Unit = {
+ checkpointers.put(shardId, checkpointer)
+ }
+
+ /**
+ * Stop tracking the specified shardId.
+ *
+ * If a checkpointer is provided, e.g. on IRecordProcessor.shutdown
[[ShutdownReason.TERMINATE]],
+ * we will use that to make the final checkpoint. If `null` is provided,
we will not make the
+ * checkpoint, e.g. in case of [[ShutdownReason.ZOMBIE]].
+ */
+ def removeCheckpointer(shardId: String, checkpointer:
IRecordProcessorCheckpointer): Unit = {
+ checkpoint(shardId, Option(checkpointer))
+ checkpointers.remove(shardId)
+ }
+
+ /** Perform the checkpoint. Exposed for tests. */
+ private[kinesis] def checkpoint(
+ shardId: String,
+ checkpointer: Option[IRecordProcessorCheckpointer]): Unit = {
--- End diff --
You mean `checkpointers`? I want `checkpoint` to be called during the
shutdown of a record processor called as well, independent from the checkpoint
time. Otherwise we have to keep track of, Should I invalidate this checkpointer
for shardId
---
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
