Skip to content

Add Backlog Metrics to Kafka Splittable DoFn Implementation #31281

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
johnjcasey merged 2 commits into from
May 28, 2024
Merged

Add Backlog Metrics to Kafka Splittable DoFn Implementation #31281

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bf28c41
Set backlog in gauge metric
Apr 30, 2024
97a8fc9
add backlog metrics to splittable dofn Kafka read implementatino
May 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions sdks/java/io/kafka/src/main/java/org/apache/beam/sdk/io/kafka/ReadFromKafkaDoFn.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@
import org.apache.beam.sdk.io.kafka.KafkaUnboundedReader.TimestampPolicyContext;
import org.apache.beam.sdk.io.range.OffsetRange;
import org.apache.beam.sdk.metrics.Distribution;
import org.apache.beam.sdk.metrics.Gauge;
import org.apache.beam.sdk.metrics.Metrics;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.SerializableFunction;
Expand Down Expand Up @@ -222,6 +223,9 @@ private ReadFromKafkaDoFn(

private transient @Nullable LoadingCache<TopicPartition, AverageRecordSize> avgRecordSize;
private static final long DEFAULT_KAFKA_POLL_TIMEOUT = 2L;

private HashMap<String, Long> perPartitionBacklogMetrics = new HashMap<String, Long>();;

@VisibleForTesting final long consumerPollingTimeout;
@VisibleForTesting final DeserializerProvider<K> keyDeserializerProvider;
@VisibleForTesting final DeserializerProvider<V> valueDeserializerProvider;
Expand Down Expand Up @@ -342,6 +346,13 @@ public double getSize(
if (!avgRecordSize.asMap().containsKey(kafkaSourceDescriptor.getTopicPartition())) {
return numRecords;
}
if (offsetEstimatorCache != null) {
for (Map.Entry<TopicPartition, KafkaLatestOffsetEstimator> tp :
offsetEstimatorCache.entrySet()) {
perPartitionBacklogMetrics.put(tp.getKey().toString(), tp.getValue().estimate());
}
}

return avgRecordSize.get(kafkaSourceDescriptor.getTopicPartition()).getTotalSize(numRecords);
}

Expand Down Expand Up @@ -394,6 +405,13 @@ public ProcessContinuation processElement(
Metrics.distribution(
METRIC_NAMESPACE,
RAW_SIZE_METRIC_PREFIX + kafkaSourceDescriptor.getTopicPartition().toString());
for (Map.Entry<String, Long> backlogSplit : perPartitionBacklogMetrics.entrySet()) {
Gauge backlog =
Metrics.gauge(
METRIC_NAMESPACE, RAW_SIZE_METRIC_PREFIX + "backlogBytes_" + backlogSplit.getKey());
backlog.set(backlogSplit.getValue());
}

// Stop processing current TopicPartition when it's time to stop.
if (checkStopReadingFn != null
&& checkStopReadingFn.apply(kafkaSourceDescriptor.getTopicPartition())) {
Expand Down