Skip to content
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

Jump to bottom

[BEAM-1512] Optimize leaf transforms materialization #2046

Closed
wants to merge 1 commit into from
Closed

[BEAM-1512] Optimize leaf transforms materialization #2046

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 9 additions & 1 deletion runners/spark/src/main/java/org/apache/beam/runners/spark/translation/BoundedDataset.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@

import com.google.common.base.Function;
import com.google.common.collect.Iterables;
import java.util.Iterator;
import java.util.List;
import javax.annotation.Nullable;
import org.apache.beam.runners.spark.coders.CoderHelpers;
Expand All @@ -32,6 +33,7 @@
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaRDDLike;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.VoidFunction;
import org.apache.spark.storage.StorageLevel;

/**
Expand Down Expand Up @@ -104,7 +106,13 @@ public void cache(String storageLevel) {

@Override
public void action() {
rdd.count();
// Empty function to force computation of RDD.
rdd.foreachPartition(new VoidFunction<Iterator<WindowedValue<T>>>() {
@Override
public void call(Iterator<WindowedValue<T>> windowedValueIterator) throws Exception {
// Empty implementation.
}
});
}

@Override
Expand Down
9 changes: 2 additions & 7 deletions ...k/src/main/java/org/apache/beam/runners/spark/translation/streaming/UnboundedDataset.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,6 @@
import org.apache.beam.sdk.coders.Coder;
import org.apache.beam.sdk.util.WindowedValue;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.VoidFunction;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import org.slf4j.Logger;
Expand Down Expand Up @@ -99,12 +98,8 @@ public void cache(String storageLevel) {

@Override
public void action() {
dStream.foreachRDD(new VoidFunction<JavaRDD<WindowedValue<T>>>() {
@Override
public void call(JavaRDD<WindowedValue<T>> rdd) throws Exception {
rdd.count();
}
});
// Force computation of DStream.
dStream.dstream().register();
}

@Override
Expand Down