arunpandianp commented on code in PR #39961:
URL: https://github.com/apache/beam/pull/39961#discussion_r4018911419
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/PubsubDynamicSink.java:
##########
@@ -127,32 +134,52 @@ public long add(WindowedValue<PubsubMessage> data) throws
IOException {
!dataTopic.isEmpty(), "No topic set for message when using dynamic
topics.");
ByteString byteString = getDataFromMessage(data.getValue(), stream);
Windmill.PubSubMessageBundle.Builder builder =
- outputBuilders.computeIfAbsent(
- dataTopic,
- topic ->
- context
- .getOutputBuilder()
- .addPubsubMessagesBuilder()
- .setTopic(topic)
- .setTimestampLabel(timestampLabel)
- .setIdLabel(idLabel)
- .setWithAttributes(true));
+ outputBuilders.computeIfAbsent(dataTopic, this::createOutputBuilder);
builder.addMessages(
Windmill.Message.newBuilder()
.setData(byteString)
.setTimestamp(WindmillTimeUtils.harnessToWindmillTimestamp(data.getTimestamp()))
.build());
+ bufferedBytes += byteString.size();
+
return byteString.size();
}
+ private void flush(boolean bundleLevel) {
+ try {
+ for (Windmill.PubSubMessageBundle.Builder builder :
outputBuilders.values()) {
+ if (builder.getMessagesCount() > 0) {
+ Windmill.PubSubMessageBundle pubsubMessages = builder.build();
+ if (bundleLevel) {
+ context.addBundlePubsubMessages(pubsubMessages);
+ } else {
+ context.getOutputBuilder().addPubsubMessages(pubsubMessages);
+ }
+ }
+ }
+ } finally {
+ outputBuilders.clear();
+ bufferedBytes = 0;
+ }
+ }
+
+ @Override
+ public void finishKey(@Nullable Object key) throws IOException {
+ if (context.multiKeyBundleEnabled() && bufferedBytes >=
MAX_PUBSUB_BUNDLE_BYTES) {
+ flush(/* bundleLevel= */ false);
Review Comment:
> why not flush at bundle level?
Wanted to spread the load across many keys. The bundle level productions
eventually get attached to an arbitrary key in the backend and having lots of
productions on a single key could run into limits or cause load skew.
--
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]
