nicktelford commented on code in PR #20954:
URL: https://github.com/apache/kafka/pull/20954#discussion_r2845780162
##########
streams/src/main/java/org/apache/kafka/streams/processor/internals/TaskManager.java:
##########
@@ -1242,35 +1239,20 @@ public void signalResume() {
* Does not include stateless or non-logged tasks.
*/
public Map<TaskId, Long> taskOffsetSums() {
- final Map<TaskId, Long> taskOffsetSums = new HashMap<>();
// Not all tasks will create directories, and there may be directories
for tasks we don't currently own,
// so we consider all tasks that are either owned or on disk. This
includes stateless tasks, which should
// just have an empty changelogOffsets map.
final Map<TaskId, Task> tasks = allTasks();
final Set<TaskId>
lockedTaskDirectoriesOfNonOwnedTasksAndClosedAndCreatedTasks =
union(HashSet::new, lockedTaskDirectories, tasks.keySet());
- for (final Task task : tasks.values()) {
- if (task.state() != State.CREATED && task.state() != State.CLOSED)
{
- final Map<TopicPartition, Long> changelogOffsets =
task.changelogOffsets();
- if (changelogOffsets.isEmpty()) {
- log.debug("Skipping to encode apparently stateless (or
non-logged) offset sum for task {}",
- task.id());
- } else {
- taskOffsetSums.put(task.id(),
sumOfChangelogOffsets(task.id(), changelogOffsets));
- }
-
lockedTaskDirectoriesOfNonOwnedTasksAndClosedAndCreatedTasks.remove(task.id());
- }
- }
- for (final TaskId id :
lockedTaskDirectoriesOfNonOwnedTasksAndClosedAndCreatedTasks) {
- final File checkpointFile = stateDirectory.checkpointFileFor(id);
- try {
- if (checkpointFile.exists()) {
- taskOffsetSums.put(id, sumOfChangelogOffsets(id, new
OffsetCheckpoint(checkpointFile).read()));
- }
- } catch (final IOException e) {
- log.warn(String.format("Exception caught while trying to read
checkpoint for task %s:", id), e);
+ final Map<TaskId, Long> taskOffsetSums =
stateDirectory.taskOffsetSums(lockedTaskDirectoriesOfNonOwnedTasksAndClosedAndCreatedTasks);
+
+ // overlay latest offsets from assigned tasks
+ for (final Task task : tasks.values()) {
+ if (task.isActive() && task.state() == State.RUNNING &&
taskOffsetSums.put(task.id(), Task.LATEST_OFFSET) == null) {
+ log.error("Could not find cached offset for assigned ACTIVE
Task {}", task.id());
Review Comment:
@bbejeck I've removed this log message, fixed the bug, added a test for it
and rebased against trunk, as requested.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
