Exemplo n.º 1
0
  @Test
  public void testChannelSelectors() {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

    DataStreamSource<Long> src = env.generateSequence(0, 0);

    DataStream<Long> broadcast = src.broadcast();
    DataStreamSink<Long> broadcastSink = broadcast.print();
    StreamPartitioner<?> broadcastPartitioner =
        env.getStreamGraph()
            .getStreamEdges(src.getId(), broadcastSink.getTransformation().getId())
            .get(0)
            .getPartitioner();
    assertTrue(broadcastPartitioner instanceof BroadcastPartitioner);

    DataStream<Long> shuffle = src.shuffle();
    DataStreamSink<Long> shuffleSink = shuffle.print();
    StreamPartitioner<?> shufflePartitioner =
        env.getStreamGraph()
            .getStreamEdges(src.getId(), shuffleSink.getTransformation().getId())
            .get(0)
            .getPartitioner();
    assertTrue(shufflePartitioner instanceof ShufflePartitioner);

    DataStream<Long> forward = src.forward();
    DataStreamSink<Long> forwardSink = forward.print();
    StreamPartitioner<?> forwardPartitioner =
        env.getStreamGraph()
            .getStreamEdges(src.getId(), forwardSink.getTransformation().getId())
            .get(0)
            .getPartitioner();
    assertTrue(forwardPartitioner instanceof ForwardPartitioner);

    DataStream<Long> rebalance = src.rebalance();
    DataStreamSink<Long> rebalanceSink = rebalance.print();
    StreamPartitioner<?> rebalancePartitioner =
        env.getStreamGraph()
            .getStreamEdges(src.getId(), rebalanceSink.getTransformation().getId())
            .get(0)
            .getPartitioner();
    assertTrue(rebalancePartitioner instanceof RebalancePartitioner);

    DataStream<Long> global = src.global();
    DataStreamSink<Long> globalSink = global.print();
    StreamPartitioner<?> globalPartitioner =
        env.getStreamGraph()
            .getStreamEdges(src.getId(), globalSink.getTransformation().getId())
            .get(0)
            .getPartitioner();
    assertTrue(globalPartitioner instanceof GlobalPartitioner);
  }
Exemplo n.º 2
0
  @Test
  public void sinkKeyTest() {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

    DataStreamSink<Long> sink = env.generateSequence(1, 100).print();
    assertTrue(
        env.getStreamGraph().getStreamNode(sink.getTransformation().getId()).getStatePartitioner()
            == null);
    assertTrue(
        env.getStreamGraph()
                .getStreamNode(sink.getTransformation().getId())
                .getInEdges()
                .get(0)
                .getPartitioner()
            instanceof ForwardPartitioner);

    KeySelector<Long, Long> key1 =
        new KeySelector<Long, Long>() {

          private static final long serialVersionUID = 1L;

          @Override
          public Long getKey(Long value) throws Exception {
            return (long) 0;
          }
        };

    DataStreamSink<Long> sink2 = env.generateSequence(1, 100).keyBy(key1).print();

    assertTrue(
        env.getStreamGraph().getStreamNode(sink2.getTransformation().getId()).getStatePartitioner()
            != null);
    assertEquals(
        key1,
        env.getStreamGraph()
            .getStreamNode(sink2.getTransformation().getId())
            .getStatePartitioner());
    assertTrue(
        env.getStreamGraph()
                .getStreamNode(sink2.getTransformation().getId())
                .getInEdges()
                .get(0)
                .getPartitioner()
            instanceof HashPartitioner);

    KeySelector<Long, Long> key2 =
        new KeySelector<Long, Long>() {

          private static final long serialVersionUID = 1L;

          @Override
          public Long getKey(Long value) throws Exception {
            return (long) 0;
          }
        };

    DataStreamSink<Long> sink3 = env.generateSequence(1, 100).keyBy(key2).print();

    assertTrue(
        env.getStreamGraph().getStreamNode(sink3.getTransformation().getId()).getStatePartitioner()
            != null);
    assertEquals(
        key2,
        env.getStreamGraph()
            .getStreamNode(sink3.getTransformation().getId())
            .getStatePartitioner());
    assertTrue(
        env.getStreamGraph()
                .getStreamNode(sink3.getTransformation().getId())
                .getInEdges()
                .get(0)
                .getPartitioner()
            instanceof HashPartitioner);
  }
Exemplo n.º 3
0
  @Test
  public void operatorTest() {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

    DataStreamSource<Long> src = env.generateSequence(0, 0);

    MapFunction<Long, Integer> mapFunction =
        new MapFunction<Long, Integer>() {
          @Override
          public Integer map(Long value) throws Exception {
            return null;
          }
        };
    DataStream<Integer> map = src.map(mapFunction);
    map.addSink(new NoOpSink<Integer>());
    assertEquals(mapFunction, getFunctionForDataStream(map));

    FlatMapFunction<Long, Integer> flatMapFunction =
        new FlatMapFunction<Long, Integer>() {
          private static final long serialVersionUID = 1L;

          @Override
          public void flatMap(Long value, Collector<Integer> out) throws Exception {}
        };
    DataStream<Integer> flatMap = src.flatMap(flatMapFunction);
    flatMap.addSink(new NoOpSink<Integer>());
    assertEquals(flatMapFunction, getFunctionForDataStream(flatMap));

    FilterFunction<Integer> filterFunction =
        new FilterFunction<Integer>() {
          @Override
          public boolean filter(Integer value) throws Exception {
            return false;
          }
        };

    DataStream<Integer> unionFilter = map.union(flatMap).filter(filterFunction);

    unionFilter.addSink(new NoOpSink<Integer>());

    assertEquals(filterFunction, getFunctionForDataStream(unionFilter));

    try {
      env.getStreamGraph().getStreamEdge(map.getId(), unionFilter.getId());
    } catch (RuntimeException e) {
      fail(e.getMessage());
    }

    try {
      env.getStreamGraph().getStreamEdge(flatMap.getId(), unionFilter.getId());
    } catch (RuntimeException e) {
      fail(e.getMessage());
    }

    OutputSelector<Integer> outputSelector =
        new OutputSelector<Integer>() {
          @Override
          public Iterable<String> select(Integer value) {
            return null;
          }
        };

    SplitStream<Integer> split = unionFilter.split(outputSelector);
    split.select("dummy").addSink(new NoOpSink<Integer>());
    List<OutputSelector<?>> outputSelectors =
        env.getStreamGraph().getStreamNode(unionFilter.getId()).getOutputSelectors();
    assertEquals(1, outputSelectors.size());
    assertEquals(outputSelector, outputSelectors.get(0));

    DataStream<Integer> select = split.select("a");
    DataStreamSink<Integer> sink = select.print();

    StreamEdge splitEdge =
        env.getStreamGraph().getStreamEdge(unionFilter.getId(), sink.getTransformation().getId());
    assertEquals("a", splitEdge.getSelectedNames().get(0));

    ConnectedStreams<Integer, Integer> connect = map.connect(flatMap);
    CoMapFunction<Integer, Integer, String> coMapper =
        new CoMapFunction<Integer, Integer, String>() {
          private static final long serialVersionUID = 1L;

          @Override
          public String map1(Integer value) {
            return null;
          }

          @Override
          public String map2(Integer value) {
            return null;
          }
        };
    DataStream<String> coMap = connect.map(coMapper);
    coMap.addSink(new NoOpSink<String>());
    assertEquals(coMapper, getFunctionForDataStream(coMap));

    try {
      env.getStreamGraph().getStreamEdge(map.getId(), coMap.getId());
    } catch (RuntimeException e) {
      fail(e.getMessage());
    }

    try {
      env.getStreamGraph().getStreamEdge(flatMap.getId(), coMap.getId());
    } catch (RuntimeException e) {
      fail(e.getMessage());
    }
  }
Exemplo n.º 4
0
  /** Tests whether parallelism gets set. */
  @Test
  public void testParallelism() {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

    DataStreamSource<Tuple2<Long, Long>> src = env.fromElements(new Tuple2<>(0L, 0L));
    env.setParallelism(10);

    SingleOutputStreamOperator<Long, ?> map =
        src.map(
                new MapFunction<Tuple2<Long, Long>, Long>() {
                  @Override
                  public Long map(Tuple2<Long, Long> value) throws Exception {
                    return null;
                  }
                })
            .name("MyMap");

    DataStream<Long> windowed =
        map.windowAll(GlobalWindows.create())
            .trigger(PurgingTrigger.of(CountTrigger.of(10)))
            .fold(
                0L,
                new FoldFunction<Long, Long>() {
                  @Override
                  public Long fold(Long accumulator, Long value) throws Exception {
                    return null;
                  }
                });

    windowed.addSink(new NoOpSink<Long>());

    DataStreamSink<Long> sink =
        map.addSink(
            new SinkFunction<Long>() {
              private static final long serialVersionUID = 1L;

              @Override
              public void invoke(Long value) throws Exception {}
            });

    assertEquals(1, env.getStreamGraph().getStreamNode(src.getId()).getParallelism());
    assertEquals(10, env.getStreamGraph().getStreamNode(map.getId()).getParallelism());
    assertEquals(1, env.getStreamGraph().getStreamNode(windowed.getId()).getParallelism());
    assertEquals(
        10, env.getStreamGraph().getStreamNode(sink.getTransformation().getId()).getParallelism());

    env.setParallelism(7);

    // Some parts, such as windowing rely on the fact that previous operators have a parallelism
    // set when instantiating the Discretizer. This would break if we dynamically changed
    // the parallelism of operations when changing the setting on the Execution Environment.
    assertEquals(1, env.getStreamGraph().getStreamNode(src.getId()).getParallelism());
    assertEquals(10, env.getStreamGraph().getStreamNode(map.getId()).getParallelism());
    assertEquals(1, env.getStreamGraph().getStreamNode(windowed.getId()).getParallelism());
    assertEquals(
        10, env.getStreamGraph().getStreamNode(sink.getTransformation().getId()).getParallelism());

    try {
      src.setParallelism(3);
      fail();
    } catch (IllegalArgumentException success) {
      // do nothing
    }

    DataStreamSource<Long> parallelSource = env.generateSequence(0, 0);
    parallelSource.addSink(new NoOpSink<Long>());
    assertEquals(7, env.getStreamGraph().getStreamNode(parallelSource.getId()).getParallelism());

    parallelSource.setParallelism(3);
    assertEquals(3, env.getStreamGraph().getStreamNode(parallelSource.getId()).getParallelism());

    map.setParallelism(2);
    assertEquals(2, env.getStreamGraph().getStreamNode(map.getId()).getParallelism());

    sink.setParallelism(4);
    assertEquals(
        4, env.getStreamGraph().getStreamNode(sink.getTransformation().getId()).getParallelism());
  }