Github user zentol commented on a diff in the pull request: https://github.com/apache/flink/pull/2707#discussion_r86109608 --- Diff: flink-streaming-java/src/main/java/org/apache/flink/streaming/runtime/operators/GenericWriteAheadSink.java --- @@ -142,46 +184,62 @@ private void cleanState() throws Exception { public void notifyOfCompletedCheckpoint(long checkpointId) throws Exception { super.notifyOfCompletedCheckpoint(checkpointId); - synchronized (state.pendingHandles) { - Set<Long> pastCheckpointIds = state.pendingHandles.keySet(); - Set<Long> checkpointsToRemove = new HashSet<>(); - for (Long pastCheckpointId : pastCheckpointIds) { + synchronized (pendingHandles) { + Set<PendingCheckpointId> checkpointsToRemove = new HashSet<>(); + + for (Map.Entry<PendingCheckpointId, PendingHandle> pendingHandle : pendingHandles.entrySet()) { + + PendingCheckpointId pendingId = pendingHandle.getKey(); + long pastCheckpointId = pendingId.checkpointId; + int subtaskId = pendingId.subtaskId; + if (pastCheckpointId <= checkpointId) { + + PendingHandle handle = pendingHandle.getValue(); + long timestamp = handle.timestamp; + StreamStateHandle streamHandle = handle.stateHandle; + try { - if (!committer.isCheckpointCommitted(pastCheckpointId)) { - Tuple2<Long, StreamStateHandle> handle = state.pendingHandles.get(pastCheckpointId); - try (FSDataInputStream in = handle.f1.openInputStream()) { + if (!committer.isCheckpointCommitted(subtaskId, pastCheckpointId)) { + try (FSDataInputStream in = streamHandle.openInputStream()) { boolean success = sendValues( new ReusingMutableToRegularIteratorWrapper<>( new InputViewIterator<>( new DataInputViewStreamWrapper( in), serializer), serializer), - handle.f0); - if (success) { //if the sending has failed we will retry on the next notify - committer.commitCheckpoint(pastCheckpointId); - checkpointsToRemove.add(pastCheckpointId); + timestamp); + if (success) { + // in case the checkpoint was successfully committed, discard its state from the + // backend and mark it for removal + // in case it failed, we retry on the next checkpoint + + committer.commitCheckpoint(subtaskId, pastCheckpointId); + streamHandle.discardState(); + checkpointsToRemove.add(pendingId); } } } else { - checkpointsToRemove.add(pastCheckpointId); + streamHandle.discardState(); + checkpointsToRemove.add(pendingId); } } catch (Exception e) { + // we have to break here to prevent a new (later) checkpoint + // from being committed before this one LOG.error("Could not commit checkpoint.", e); - break; // we have to break here to prevent a new checkpoint from being committed before this one + break; } } } - for (Long toRemove : checkpointsToRemove) { - Tuple2<Long, StreamStateHandle> handle = state.pendingHandles.get(toRemove); - state.pendingHandles.remove(toRemove); - handle.f1.discardState(); + + // ...finally remove the checkpoints that are marked as committed --- End diff -- unnecessary comment
--- 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. ---