Skip to content

fix: preserve duplicate same-timestamp elements in FlinkOrderedListState #39783

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

Open
waterWang wants to merge 1 commit into
base: master
Choose a base branch
from
+15 −7
Open

fix: preserve duplicate same-timestamp elements in FlinkOrderedListState #39783

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
22 changes: 15 additions & 7 deletions ...g/apache/beam/runners/flink/translation/wrappers/streaming/state/FlinkStateInternals.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,11 @@
import java.io.IOException;
import java.util.Collections;
import java.util.HashSet;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
import java.util.Objects;
import java.util.Set;
import java.util.SortedMap;
Expand Down Expand Up @@ -620,18 +623,21 @@ private static class FlinkOrderedListState<T> implements OrderedListState<T> {

@Override
public Iterable<TimestampedValue<T>> readRange(Instant minTimestamp, Instant limitTimestamp) {
return readAsMap().subMap(minTimestamp, limitTimestamp).values();
return readAsMultimap().subMap(minTimestamp, limitTimestamp).values().stream()
.flatMap(List::stream)
.collect(Collectors.toList());
}

@Override
public void clearRange(Instant minTimestamp, Instant limitTimestamp) {
SortedMap<Instant, TimestampedValue<T>> sortedMap = readAsMap();
SortedMap<Instant, List<TimestampedValue<T>>> sortedMap = readAsMultimap();
sortedMap.subMap(minTimestamp, limitTimestamp).clear();
try {
ListState<TimestampedValue<T>> partitionedState =
flinkStateBackend.getPartitionedState(
namespace, namespaceSerializer, flinkStateDescriptor);
partitionedState.update(Lists.newArrayList(sortedMap.values()));
partitionedState.update(
sortedMap.values().stream().flatMap(List::stream).collect(Collectors.toList()));
} catch (Exception e) {
throw new RuntimeException("Error adding to bag state.", e);
}
Expand Down Expand Up @@ -680,10 +686,12 @@ public ReadableState<Boolean> readLater() {
@Override
@Nullable
public Iterable<TimestampedValue<T>> read() {
return readAsMap().values();
return readAsMultimap().values().stream()
.flatMap(List::stream)
.collect(Collectors.toList());
}

private SortedMap<Instant, TimestampedValue<T>> readAsMap() {
private SortedMap<Instant, List<TimestampedValue<T>>> readAsMultimap() {
Iterable<TimestampedValue<T>> listValues;
try {
ListState<TimestampedValue<T>> partitionedState =
Expand All @@ -694,9 +702,9 @@ private SortedMap<Instant, TimestampedValue<T>> readAsMap() {
throw new RuntimeException("Error reading state.", e);
}

SortedMap<Instant, TimestampedValue<T>> sortedMap = Maps.newTreeMap();
SortedMap<Instant, List<TimestampedValue<T>>> sortedMap = Maps.newTreeMap();
for (TimestampedValue<T> value : listValues) {
sortedMap.put(value.getTimestamp(), value);
sortedMap.computeIfAbsent(value.getTimestamp(), k -> new ArrayList<>()).add(value);
}
return sortedMap;
}
Expand Down
Loading