use of org.apache.flink.api.common.state.MapStateDescriptor in project flink by apache.
the class StreamGraphGeneratorTest method testUnalignedCheckpointDisabledOnBroadcast.
@Test
public void testUnalignedCheckpointDisabledOnBroadcast() {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(42);
DataStream<Long> source1 = env.fromSequence(1L, 10L);
DataStream<Long> map1 = source1.broadcast().map(l -> l);
DataStream<Long> source2 = env.fromSequence(2L, 11L);
DataStream<Long> keyed = source2.keyBy(r -> 0L);
final MapStateDescriptor<Long, Long> descriptor = new MapStateDescriptor<>("broadcast", BasicTypeInfo.LONG_TYPE_INFO, BasicTypeInfo.LONG_TYPE_INFO);
final BroadcastStream<Long> broadcast = map1.broadcast(descriptor);
final SingleOutputStreamOperator<Long> joined = keyed.connect(broadcast).process(new KeyedBroadcastProcessFunction<Long, Long, Long, Long>() {
@Override
public void processElement(Long value, ReadOnlyContext ctx, Collector<Long> out) {
}
@Override
public void processBroadcastElement(Long value, Context ctx, Collector<Long> out) {
}
});
StreamGraph streamGraph = env.getStreamGraph();
assertEquals(4, streamGraph.getStreamNodes().size());
// single broadcast
assertThat(edge(streamGraph, source1, map1), supportsUnalignedCheckpoints(false));
// keyed, connected with broadcast
assertThat(edge(streamGraph, source2, joined), supportsUnalignedCheckpoints(false));
// broadcast, connected with keyed
assertThat(edge(streamGraph, map1, joined), supportsUnalignedCheckpoints(false));
}
use of org.apache.flink.api.common.state.MapStateDescriptor in project flink by apache.
the class SavepointStateBackendSwitchTestBase method switchStateBackend.
@Test
public void switchStateBackend() throws Exception {
final File pathToWrite = tempFolder.newFile();
final MapStateDescriptor<Long, Long> mapStateDescriptor = new MapStateDescriptor<>("my-map-state", Long.class, Long.class);
mapStateDescriptor.initializeSerializerUnlessSet(new ExecutionConfig());
final ValueStateDescriptor<Long> valueStateDescriptor = new ValueStateDescriptor<>("my-value-state", Long.class);
valueStateDescriptor.initializeSerializerUnlessSet(new ExecutionConfig());
final ListStateDescriptor<Long> listStateDescriptor = new ListStateDescriptor<>("my-list-state", Long.class);
listStateDescriptor.initializeSerializerUnlessSet(new ExecutionConfig());
final Integer namespace1 = 1;
final Integer namespace2 = 2;
final Integer namespace3 = 3;
final Integer namespace4 = 4;
try (final CheckpointableKeyedStateBackend<String> keyedBackend = fromBackend.createBackend(KEY_GROUP_RANGE, NUM_KEY_GROUPS, Collections.emptyList())) {
takeSavepoint(keyedBackend, pathToWrite, mapStateDescriptor, valueStateDescriptor, listStateDescriptor, namespace1, namespace2, namespace3, namespace4);
}
final SnapshotResult<KeyedStateHandle> stateHandles;
try (BufferedInputStream bis = new BufferedInputStream((new FileInputStream(pathToWrite)))) {
stateHandles = InstantiationUtil.deserializeObject(bis, Thread.currentThread().getContextClassLoader());
}
final KeyedStateHandle stateHandle = stateHandles.getJobManagerOwnedSnapshot();
try (final CheckpointableKeyedStateBackend<String> keyedBackend = toBackend.createBackend(KEY_GROUP_RANGE, NUM_KEY_GROUPS, StateObjectCollection.singleton(stateHandle))) {
verifyRestoredState(mapStateDescriptor, valueStateDescriptor, listStateDescriptor, namespace1, namespace2, namespace3, namespace4, keyedBackend);
}
}
use of org.apache.flink.api.common.state.MapStateDescriptor in project flink by apache.
the class BroadcastStateITCase method testBroadcastTranslation.
@Test
public void testBroadcastTranslation() throws Exception {
final MapStateDescriptor<Long, String> utterDescriptor = new MapStateDescriptor<>("broadcast-state", BasicTypeInfo.LONG_TYPE_INFO, BasicTypeInfo.STRING_TYPE_INFO);
final Map<Long, String> expected = new HashMap<>();
expected.put(0L, "test:0");
expected.put(1L, "test:1");
expected.put(2L, "test:2");
expected.put(3L, "test:3");
expected.put(4L, "test:4");
expected.put(5L, "test:5");
final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
final DataStream<Long> srcOne = env.generateSequence(0L, 5L).assignTimestampsAndWatermarks(new CustomWmEmitter<Long>() {
private static final long serialVersionUID = -8500904795760316195L;
@Override
public long extractTimestamp(Long element, long previousElementTimestamp) {
return element;
}
});
final DataStream<String> srcTwo = env.fromCollection(expected.values()).assignTimestampsAndWatermarks(new CustomWmEmitter<String>() {
private static final long serialVersionUID = -2148318224248467213L;
@Override
public long extractTimestamp(String element, long previousElementTimestamp) {
return Long.parseLong(element.split(":")[1]);
}
});
final BroadcastStream<String> broadcast = srcTwo.broadcast(utterDescriptor);
// the timestamp should be high enough to trigger the timer after all the elements arrive.
final DataStream<String> output = srcOne.connect(broadcast).process(new TestBroadcastProcessFunction());
output.addSink(new TestSink(0)).setParallelism(1);
env.execute();
}
use of org.apache.flink.api.common.state.MapStateDescriptor in project flink by apache.
the class BroadcastStateITCase method testKeyedWithBroadcastTranslation.
@Test
public void testKeyedWithBroadcastTranslation() throws Exception {
final MapStateDescriptor<Long, String> utterDescriptor = new MapStateDescriptor<>("broadcast-state", BasicTypeInfo.LONG_TYPE_INFO, BasicTypeInfo.STRING_TYPE_INFO);
final Map<Long, String> expected = new HashMap<>();
expected.put(0L, "test:0");
expected.put(1L, "test:1");
expected.put(2L, "test:2");
expected.put(3L, "test:3");
expected.put(4L, "test:4");
expected.put(5L, "test:5");
final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
final DataStream<Long> srcOne = env.generateSequence(0L, 5L).assignTimestampsAndWatermarks(new CustomWmEmitter<Long>() {
private static final long serialVersionUID = -8500904795760316195L;
@Override
public long extractTimestamp(Long element, long previousElementTimestamp) {
return element;
}
}).keyBy((KeySelector<Long, Long>) value -> value);
final DataStream<String> srcTwo = env.fromCollection(expected.values()).assignTimestampsAndWatermarks(new CustomWmEmitter<String>() {
private static final long serialVersionUID = -2148318224248467213L;
@Override
public long extractTimestamp(String element, long previousElementTimestamp) {
return Long.parseLong(element.split(":")[1]);
}
});
final BroadcastStream<String> broadcast = srcTwo.broadcast(utterDescriptor);
// the timestamp should be high enough to trigger the timer after all the elements arrive.
final DataStream<String> output = srcOne.connect(broadcast).process(new TestKeyedBroadcastProcessFunction(100000L, expected));
output.addSink(new TestSink(expected.size())).setParallelism(1);
env.execute();
}
use of org.apache.flink.api.common.state.MapStateDescriptor in project flink by apache.
the class SortingBoundedInputITCase method testBatchExecutionWithTimersOneInput.
@Test
public void testBatchExecutionWithTimersOneInput() {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// set parallelism to 1 to have consistent order of results
env.setParallelism(1);
Configuration config = new Configuration();
config.set(ExecutionOptions.RUNTIME_MODE, RuntimeExecutionMode.BATCH);
env.configure(config, this.getClass().getClassLoader());
WatermarkStrategy<Tuple2<Integer, Integer>> watermarkStrategy = WatermarkStrategy.forGenerator(ctx -> GENERATE_WATERMARK_AFTER_4_14_TIMESTAMP).withTimestampAssigner((r, previousTimestamp) -> r.f1);
SingleOutputStreamOperator<Tuple2<Integer, Integer>> elements = env.fromElements(Tuple2.of(1, 3), Tuple2.of(1, 1), Tuple2.of(2, 1), Tuple2.of(1, 4), // late element
Tuple2.of(2, 3), // late element
Tuple2.of(1, 2), Tuple2.of(1, 13), Tuple2.of(1, 11), Tuple2.of(2, 14), // late element
Tuple2.of(1, 11)).assignTimestampsAndWatermarks(watermarkStrategy);
OutputTag<Integer> lateElements = new OutputTag<>("late_elements", BasicTypeInfo.INT_TYPE_INFO);
SingleOutputStreamOperator<Tuple3<Long, Integer, Integer>> sums = elements.map(element -> element.f0).keyBy(element -> element).process(new KeyedProcessFunction<Integer, Integer, Tuple3<Long, Integer, Integer>>() {
private MapState<Long, Integer> countState;
private ValueState<Long> previousTimestampState;
@Override
public void open(Configuration parameters) {
countState = getRuntimeContext().getMapState(new MapStateDescriptor<>("sum", BasicTypeInfo.LONG_TYPE_INFO, BasicTypeInfo.INT_TYPE_INFO));
previousTimestampState = getRuntimeContext().getState(new ValueStateDescriptor<>("previousTimestamp", BasicTypeInfo.LONG_TYPE_INFO));
}
@Override
public void processElement(Integer value, Context ctx, Collector<Tuple3<Long, Integer, Integer>> out) throws Exception {
Long elementTimestamp = ctx.timestamp();
long nextTen = ((elementTimestamp + 10) / 10) * 10;
ctx.timerService().registerEventTimeTimer(nextTen);
if (elementTimestamp < ctx.timerService().currentWatermark()) {
ctx.output(lateElements, value);
} else {
Long previousTimestamp = Optional.ofNullable(previousTimestampState.value()).orElse(0L);
assertThat(elementTimestamp, greaterThanOrEqualTo(previousTimestamp));
previousTimestampState.update(elementTimestamp);
Integer currentCount = Optional.ofNullable(countState.get(nextTen)).orElse(0);
countState.put(nextTen, currentCount + 1);
}
}
@Override
public void onTimer(long timestamp, OnTimerContext ctx, Collector<Tuple3<Long, Integer, Integer>> out) throws Exception {
out.collect(Tuple3.of(timestamp, ctx.getCurrentKey(), countState.get(timestamp)));
countState.remove(timestamp);
// this would go in infinite loop if we did not quiesce the
// timer service.
ctx.timerService().registerEventTimeTimer(timestamp + 1);
}
});
DataStream<Integer> lateStream = sums.getSideOutput(lateElements);
List<Integer> lateRecordsCollected = CollectionUtil.iteratorToList(DataStreamUtils.collect(lateStream));
List<Tuple3<Long, Integer, Integer>> sumsCollected = CollectionUtil.iteratorToList(DataStreamUtils.collect(sums));
assertTrue(lateRecordsCollected.isEmpty());
assertThat(sumsCollected, equalTo(Arrays.asList(Tuple3.of(10L, 1, 4), Tuple3.of(20L, 1, 3), Tuple3.of(10L, 2, 2), Tuple3.of(20L, 2, 1))));
}
Aggregations