Github user zentol commented on a diff in the pull request:
https://github.com/apache/flink/pull/2707#discussion_r86563313
--- Diff:
flink-streaming-java/src/main/java/org/apache/flink/streaming/runtime/operators/GenericWriteAheadSink.java
---
@@ -77,111 +84,144 @@ public GenericWriteAheadSink(CheckpointCommitter
committer, TypeSerializer<IN> s
public void open() throws Exception {
super.open();
committer.setOperatorId(id);
-
committer.setOperatorSubtaskId(getRuntimeContext().getIndexOfThisSubtask());
committer.open();
- cleanState();
- checkpointStreamFactory =
-
getContainingTask().createCheckpointStreamFactory(this);
+
+ checkpointStreamFactory = getContainingTask()
+ .createCheckpointStreamFactory(this);
+
+ cleanRestoredHandles();
}
public void close() throws Exception {
committer.close();
}
/**
- * Saves a handle in the state.
+ * Called when a checkpoint barrier arrives. It closes any open streams
to the backend
+ * and marks them as pending for committing to the external,
third-party storage system.
*
- * @param checkpointId
- * @throws IOException
+ * @param checkpointId the id of the latest received checkpoint.
+ * @throws IOException in case something went wrong when handling the
stream to the backend.
*/
private void saveHandleInState(final long checkpointId, final long
timestamp) throws Exception {
+ Preconditions.checkNotNull(this.pendingCheckpoints, "The
operator has not been properly initialized.");
+
//only add handle if a new OperatorState was created since the
last snapshot
if (out != null) {
+ int subtaskIdx =
getRuntimeContext().getIndexOfThisSubtask();
StreamStateHandle handle = out.closeAndGetHandle();
- if (state.pendingHandles.containsKey(checkpointId)) {
+
+ PendingCheckpoint pendingCheckpoint = new
PendingCheckpoint(
+ checkpointId, subtaskIdx, timestamp, handle);
+
+ if (pendingCheckpoints.contains(pendingCheckpoint)) {
//we already have a checkpoint stored for that
ID that may have been partially written,
//so we discard this "alternate version" and
use the stored checkpoint
handle.discardState();
} else {
- state.pendingHandles.put(checkpointId, new
Tuple2<>(timestamp, handle));
+ pendingCheckpoints.add(pendingCheckpoint);
}
out = null;
}
}
@Override
- public void snapshotState(FSDataOutputStream out,
- long checkpointId,
- long timestamp) throws Exception {
+ public void snapshotState(FSDataOutputStream out, long checkpointId,
long timestamp) throws Exception {
saveHandleInState(checkpointId, timestamp);
- InstantiationUtil.serializeObject(out, state);
+ DataOutputViewStreamWrapper outStream = new
DataOutputViewStreamWrapper(out);
+ outStream.writeInt(pendingCheckpoints.size());
+ for (PendingCheckpoint pendingCheckpoint : pendingCheckpoints) {
+ pendingCheckpoint.serialize(outStream);
+ }
}
@Override
public void restoreState(FSDataInputStream in) throws Exception {
- this.state = InstantiationUtil.deserializeObject(in,
getUserCodeClassloader());
+ final DataInputViewStreamWrapper inStream = new
DataInputViewStreamWrapper(in);
+ int numPendingHandles = inStream.readInt();
+ for (int i = 0; i < numPendingHandles; i++) {
+
pendingCheckpoints.add(PendingCheckpoint.restore(inStream,
getUserCodeClassloader()));
+ }
}
- private void cleanState() throws Exception {
- synchronized (this.state.pendingHandles) { //remove all handles
that were already committed
- Set<Long> pastCheckpointIds =
this.state.pendingHandles.keySet();
- Set<Long> checkpointsToRemove = new HashSet<>();
- for (Long pastCheckpointId : pastCheckpointIds) {
- if
(committer.isCheckpointCommitted(pastCheckpointId)) {
-
checkpointsToRemove.add(pastCheckpointId);
+ /**
+ * Called at {@link #open()} to clean-up the pending handle list.
+ * It iterates over all restored pending handles, checks which ones are
already
+ * committed to the outside storage system and removes them from the
list.
+ */
+ private void cleanRestoredHandles() throws Exception {
+ synchronized (pendingCheckpoints) {
+
+ // for each of the pending handles...
+ Iterator<PendingCheckpoint> pendingCheckpointIt =
pendingCheckpoints.iterator();
+ while (pendingCheckpointIt.hasNext()) {
+
+ PendingCheckpoint pendingCheckpoint =
pendingCheckpointIt.next();
+ long checkpointId =
pendingCheckpoint.checkpointId;
+ int subtaskId = pendingCheckpoint.subtaskId;
+
+ //...check if the temporary buffer is already
committed and if yes,
+ // remove it from the list of pending
checkpoints.
+ if (committer.isCheckpointCommitted(subtaskId,
checkpointId)) {
+
pendingCheckpoint.stateHandle.discardState();
+ pendingCheckpointIt.remove();
--- End diff --
ah, my bad :)
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
