Github user senorcarbone commented on a diff in the pull request:
https://github.com/apache/flink/pull/1668#discussion_r108166093
--- Diff:
flink-streaming-java/src/main/java/org/apache/flink/streaming/runtime/tasks/StreamIterationHead.java
---
@@ -17,100 +17,164 @@
package org.apache.flink.streaming.runtime.tasks;
-import java.util.concurrent.ArrayBlockingQueue;
-import java.util.concurrent.BlockingQueue;
-import java.util.concurrent.TimeUnit;
-
import org.apache.flink.annotation.Internal;
import org.apache.flink.api.common.JobID;
+import org.apache.flink.api.common.state.ListState;
+import org.apache.flink.api.common.state.ListStateDescriptor;
+import org.apache.flink.runtime.checkpoint.CheckpointMetaData;
+import org.apache.flink.runtime.checkpoint.CheckpointMetrics;
+import org.apache.flink.runtime.checkpoint.CheckpointOptions;
+import org.apache.flink.runtime.io.network.api.CheckpointBarrier;
+import org.apache.flink.streaming.api.graph.StreamConfig;
+import org.apache.flink.streaming.api.operators.AbstractStreamOperator;
+import org.apache.flink.streaming.api.operators.OneInputStreamOperator;
+import org.apache.flink.streaming.api.operators.Output;
import org.apache.flink.streaming.api.watermark.Watermark;
-import org.apache.flink.streaming.runtime.io.RecordWriterOutput;
import org.apache.flink.streaming.runtime.io.BlockingQueueBroker;
+import org.apache.flink.streaming.runtime.io.RecordWriterOutput;
import org.apache.flink.streaming.runtime.streamrecord.StreamRecord;
+import org.apache.flink.types.Either;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Comparator;
+import java.util.Iterator;
+import java.util.List;
+import java.util.LinkedList;
+import java.util.concurrent.ArrayBlockingQueue;
+import java.util.concurrent.BlockingQueue;
+import java.util.concurrent.TimeUnit;
+
+/**
+ * TODO write javadoc
+ * <p>
+ * - open a list state per snapshot process
+ * - book-keep snapshot logs
+ * - Clean up state when a savepoint is complete - ONLY in-transit records
who do NOT belong in other snapshots
+ *
+ * @param <IN>
+ */
@Internal
-public class StreamIterationHead<OUT> extends OneInputStreamTask<OUT, OUT>
{
+public class StreamIterationHead<IN> extends OneInputStreamTask<IN, IN> {
private static final Logger LOG =
LoggerFactory.getLogger(StreamIterationHead.class);
private volatile boolean running = true;
- //
------------------------------------------------------------------------
-
+ private volatile RecordWriterOutput<IN>[] outputs;
+
+ private UpstreamLogger<IN> upstreamLogger;
+
+ private Object lock;
+
+ @Override
+ public void init() throws Exception {
+ this.lock = getCheckpointLock();
+ getConfiguration().setStreamOperator(new
UpstreamLogger(getConfiguration()));
+ operatorChain = new OperatorChain<>(this);
+ this.upstreamLogger = (UpstreamLogger<IN>)
operatorChain.getHeadOperator();
--- End diff --
it's another instance that is why I was fetching it back there.
The OperatorChain basically deserialises and sets up another instance
through the configuration.
---
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.
---
