arunpandianp commented on code in PR #39961:
URL: https://github.com/apache/beam/pull/39961#discussion_r4022614125
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/PubsubSink.java:
##########
@@ -187,18 +190,41 @@ public long add(WindowedValue<T> data) throws IOException
{
return byteString.size();
}
+ private void flush(boolean bundleLevel) {
+ try {
+ Windmill.PubSubMessageBundle pubsubMessages = outputBuilder.build();
+ if (pubsubMessages.getMessagesCount() > 0) {
+ if (bundleLevel) {
+ context.addBundlePubsubMessages(pubsubMessages);
+ } else {
+ context.getOutputBuilder().addPubsubMessages(pubsubMessages);
+ }
+ }
+ } finally {
+ outputBuilder = createOutputBuilder();
+ }
+ }
+
+ @Override
+ public void finishKey(@Nullable Object key) throws IOException {
+ if (context.multiKeyBundleEnabled()) {
+ flush(/* bundleLevel= */ false);
+ }
+ }
+
@Override
public void close() throws IOException {
- Windmill.PubSubMessageBundle pubsubMessages = outputBuilder.build();
- if (pubsubMessages.getMessagesCount() > 0) {
- context.getOutputBuilder().addPubsubMessages(pubsubMessages);
+ if (context.multiKeyBundleEnabled()) {
Review Comment:
done.
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/PubsubSink.java:
##########
@@ -187,18 +190,41 @@ public long add(WindowedValue<T> data) throws IOException
{
return byteString.size();
}
+ private void flush(boolean bundleLevel) {
+ try {
+ Windmill.PubSubMessageBundle pubsubMessages = outputBuilder.build();
+ if (pubsubMessages.getMessagesCount() > 0) {
+ if (bundleLevel) {
+ context.addBundlePubsubMessages(pubsubMessages);
+ } else {
+ context.getOutputBuilder().addPubsubMessages(pubsubMessages);
+ }
+ }
+ } finally {
+ outputBuilder = createOutputBuilder();
+ }
+ }
+
+ @Override
+ public void finishKey(@Nullable Object key) throws IOException {
+ if (context.multiKeyBundleEnabled()) {
+ flush(/* bundleLevel= */ false);
Review Comment:
Changed to flush at the bundle level.
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/IsmSink.java:
##########
@@ -295,6 +296,9 @@ private void finish() throws IOException {
.encode(Footer.of(startOfIndex, startOfBloomFilter,
numberOfKeysWritten), out);
}
+ @Override
+ public void finishKey(@Nullable Object key) throws IOException {}
Review Comment:
done.
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/StreamingModeExecutionContext.java:
##########
@@ -321,6 +323,8 @@ public void reset() {
// these lists and maps are returned to callers after processing
Review Comment:
done.
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/PubsubSink.java:
##########
@@ -183,22 +190,44 @@ public long add(WindowedValue<T> data) throws IOException
{
.setData(byteString)
.setTimestamp(WindmillTimeUtils.harnessToWindmillTimestamp(data.getTimestamp()))
.build());
+ bufferedBytes += byteString.size();
return byteString.size();
}
+ private void flush(boolean bundleLevel) {
+ try {
+ Windmill.PubSubMessageBundle pubsubMessages = outputBuilder.build();
+ if (pubsubMessages.getMessagesCount() > 0) {
+ if (bundleLevel) {
+ context.addBundlePubsubMessages(pubsubMessages);
+ } else {
+ context.getOutputBuilder().addPubsubMessages(pubsubMessages);
+ }
+ }
+ } finally {
+ outputBuilder = createOutputBuilder();
+ bufferedBytes = 0;
+ }
+ }
+
@Override
- public void close() throws IOException {
- Windmill.PubSubMessageBundle pubsubMessages = outputBuilder.build();
- if (pubsubMessages.getMessagesCount() > 0) {
- context.getOutputBuilder().addPubsubMessages(pubsubMessages);
+ public void finishKey(@Nullable Object key) throws IOException {
+ if (context.multiKeyBundleEnabled() && bufferedBytes >=
MAX_PUBSUB_BUNDLE_BYTES) {
Review Comment:
done.
##########
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) {
Review Comment:
done.
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/PubsubDynamicSink.java:
##########
@@ -145,14 +139,43 @@ public long add(WindowedValue<PubsubMessage> data) throws
IOException {
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();
+ }
+ }
+
+ @Override
+ public void finishKey(@Nullable Object key) throws IOException {
+ if (context.multiKeyBundleEnabled()) {
+ flush(/* bundleLevel= */ false);
+ }
+ }
+
@Override
public void close() throws IOException {
- outputBuilders.clear();
+ if (context.multiKeyBundleEnabled()) {
Review Comment:
done
##########
runners/google-cloud-dataflow-java/worker/src/main/java/org/apache/beam/runners/dataflow/worker/windmill/work/processing/StreamingWorkScheduler.java:
##########
Review Comment:
good idea! done.
##########
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:
ack. Changed to flush at bundle level.
--
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]