arunpandianp commented on code in PR #40593:
URL: https://github.com/apache/beam/pull/40593#discussion_r4296639384
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/util/BoundedQueueExecutor.java:
##########
@@ -403,25 +501,52 @@ BoundedQueueExecutorWorkHandleImpl
createBudgetHandle(Work work, long bytes) {
checkArgument(handle instanceof BoundedQueueExecutorWorkHandleImpl);
checkStateNotNull(onFailedWorkHandler);
BoundedQueueExecutorWorkHandleImpl internalHandle =
(BoundedQueueExecutorWorkHandleImpl) handle;
- if (keyGroupWorkQueue == null) {
+ @Nullable KeyGroupWorkIndex index = keyGroupWorkIndex;
+ if (index == null) {
return null;
}
while (true) {
- @Nullable QueuedWork queuedWork =
keyGroupWorkQueue.pollWork(computationId, keyGroup);
- if (queuedWork == null) {
+ @Nullable QueuedWork stolen = index.pollAndClaim(computationId,
keyGroup);
+ if (stolen == null) {
return null;
}
- Work work = queuedWork.getWork().work();
+ ExecutableWork stolenWork = stolen.getWork();
+ BoundedQueueExecutorWorkHandleImpl stolenHandle = stolen.getHandle();
+ stolen.clearClaimedWork();
+ onWorkStolen();
+ Work work = stolenWork.work();
if (work.isFailed()) {
- queuedWork.getHandle().close();
+ stolenHandle.close();
onFailedWorkHandler.onFailedWork(work);
continue;
}
- internalHandle.merge(queuedWork.getHandle());
- return queuedWork.getWork();
+ internalHandle.merge(stolenHandle);
+ return stolenWork;
}
}
+ /**
+ * Purges stale shells in bulk if they accumulate while all executor threads
are busy running
+ * multi-key bundles.
+ */
+ private void onWorkStolen() {
+ if (workQueue.size() <= (long) elementsOutstanding.get() +
maximumElementsOutstanding
Review Comment:
If there are many forceExecute calls from retries or finalizations that
don't respect the outstanding limit, jobs could reach more than
maximumElementsOutstanding items in the queue. I wanted to avoid calling
removeIf (O(n)) frequently in such cases. elementsOutstanding gives us the
count of non shell work items, so elementsOutstanding +
maximumElementsOutstanding means we allow up to maximumElementsOutstanding
number of shells before removing them at once. I'll add a comment to explain.
Let me know if you see other problems with using `elementsOutstanding`
--
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]
