use of org.apache.flink.streaming.api.watermark.Watermark in project flink by apache.
the class WindowOperatorContractTest method testProcessingElementsWithinAllowedLateness.
@Test
public void testProcessingElementsWithinAllowedLateness() throws Exception {
WindowAssigner<Integer, TimeWindow> mockAssigner = mockTimeWindowAssigner();
Trigger<Integer, TimeWindow> mockTrigger = mockTrigger();
InternalWindowFunction<Iterable<Integer>, Void, Integer, TimeWindow> mockWindowFunction = mockWindowFunction();
KeyedOneInputStreamOperatorTestHarness<Integer, Integer, Void> testHarness = createWindowOperator(mockAssigner, mockTrigger, 20L, intListDescriptor, mockWindowFunction);
testHarness.open();
when(mockAssigner.assignWindows(anyInt(), anyLong(), anyAssignerContext())).thenReturn(Arrays.asList(new TimeWindow(0, 2)));
assertEquals(0, testHarness.getOutput().size());
assertEquals(0, testHarness.numKeyedStateEntries());
doAnswer(new Answer<TriggerResult>() {
@Override
public TriggerResult answer(InvocationOnMock invocation) throws Exception {
return TriggerResult.FIRE;
}
}).when(mockTrigger).onElement(Matchers.<Integer>anyObject(), anyLong(), anyTimeWindow(), anyTriggerContext());
// 20 is just at the limit, window.maxTime() is 1 and allowed lateness is 20
testHarness.processWatermark(new Watermark(20));
testHarness.processElement(new StreamRecord<>(0, 0L));
verify(mockWindowFunction, times(1)).apply(eq(0), eq(new TimeWindow(0, 2)), intIterable(0), WindowOperatorContractTest.<Void>anyCollector());
// clear is only called at cleanup time/GC time
verify(mockTrigger, never()).clear(anyTimeWindow(), anyTriggerContext());
// FIRE should not purge contents
// window contents plus trigger state
assertEquals(1, testHarness.numKeyedStateEntries());
// just the GC timer
assertEquals(1, testHarness.numEventTimeTimers());
}
use of org.apache.flink.streaming.api.watermark.Watermark in project flink by apache.
the class StatusWatermarkValveTest method testMultipleInputValve.
/**
* Tests that valves work as expected when they handle multiple input channels (tested with 3).
* Tested behaviours are explained as inline comments.
*/
@Test
public void testMultipleInputValve() {
BufferedValveOutputHandler valveOutput = new BufferedValveOutputHandler();
StatusWatermarkValve valve = new StatusWatermarkValve(3, valveOutput);
// ------------------------------------------------------------------------
// Ensure that watermarks are output only when all
// channels have been input some watermark.
// ------------------------------------------------------------------------
valve.inputWatermark(new Watermark(0), 0);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(0), 1);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(0), 2);
assertEquals(new Watermark(0), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// ------------------------------------------------------------------------
// Ensure that watermarks are output as soon as the overall min
// watermark across all channels have advanced.
// ------------------------------------------------------------------------
valve.inputWatermark(new Watermark(12), 0);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(8), 2);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(10), 2);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(15), 1);
// lowest watermark across all channels is now channel 2, with watermark @ 10
assertEquals(new Watermark(10), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// ------------------------------------------------------------------------
// Ensure that decreasing watermarks are ignored
// ------------------------------------------------------------------------
valve.inputWatermark(new Watermark(6), 0);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// ------------------------------------------------------------------------
// Ensure that when some input channel becomes idle, that channel will
// no longer be accounted for when advancing the watermark.
// ------------------------------------------------------------------------
// marking channel 2 as IDLE shouldn't result in overall status toggle for the valve,
// because there are still other active channels (0 and 1), so there should not be any
// stream status outputs;
// also, now that channel 2 is IDLE, the overall min watermark is 12 (from channel 0),
// so the valve should output that
valve.inputStreamStatus(StreamStatus.IDLE, 2);
assertEquals(new Watermark(12), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// from now on, since channel 2 is IDLE, the valve should use watermarks only from
// channel 0 and 1 to find the min watermark, even if channel 2 has the lowest watermark (10)
valve.inputWatermark(new Watermark(17), 0);
assertEquals(new Watermark(15), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(25), 0);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(20), 1);
assertEquals(new Watermark(20), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// ------------------------------------------------------------------------
// Ensure that after some channel resumes to be ACTIVE, it needs to
// catch up" with the current overall min watermark before it can be
// accounted for again when finding the min watermark across channels.
// Also tests that before the resumed channel catches up, the overall
// min watermark can still advance with watermarks of other channels.
// ------------------------------------------------------------------------
// resuming channel 2 to be ACTIVE shouldn't result in overall status toggle for the valve,
// because the valve wasn't overall IDLE, so there should not be any stream status outputs;
valve.inputStreamStatus(StreamStatus.ACTIVE, 2);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// although watermarks for channel 2 will now be accepted, it still
// hasn't caught up with the overall min watermark (20)
valve.inputWatermark(new Watermark(18), 2);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// since channel 2 hasn't caught up yet, it is still ignored when advancing new min watermarks
valve.inputWatermark(new Watermark(22), 1);
assertEquals(new Watermark(22), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(28), 0);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(33), 1);
assertEquals(new Watermark(28), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// now, channel 2 has caught up with the overall min watermark
valve.inputWatermark(new Watermark(30), 2);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(31), 0);
// this acknowledges that channel 2's watermark is being accounted for again
assertEquals(new Watermark(30), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(34), 2);
assertEquals(new Watermark(31), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// ------------------------------------------------------------------------
// Ensure that once all channels are IDLE, the valve should also
// determine itself to be IDLE output a IDLE stream status
// ------------------------------------------------------------------------
valve.inputStreamStatus(StreamStatus.IDLE, 0);
// this is because once channel 0 becomes IDLE,
// the new min watermark will be 33 (channel 1)
assertEquals(new Watermark(33), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputStreamStatus(StreamStatus.IDLE, 2);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputStreamStatus(StreamStatus.IDLE, 1);
assertEquals(StreamStatus.IDLE, valveOutput.popLastOutputStreamStatus());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// ------------------------------------------------------------------------
// Ensure that channels gradually become ACTIVE again, the above behaviours
// still hold. Also ensure that as soon as one of the input channels
// become ACTIVE, the valve is ACTIVE again and outputs an ACTIVE stream status.
// ------------------------------------------------------------------------
// let channel 0 resume to be ACTIVE
valve.inputStreamStatus(StreamStatus.ACTIVE, 0);
assertEquals(StreamStatus.ACTIVE, valveOutput.popLastOutputStreamStatus());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// channel 0 is the only ACTIVE channel now, and is the only channel
// accounted for when advancing min watermark
valve.inputWatermark(new Watermark(36), 0);
assertEquals(new Watermark(36), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// new also let channel 1 become ACTIVE
valve.inputStreamStatus(StreamStatus.ACTIVE, 1);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// channel 1 is still behind overall min watermark
valve.inputWatermark(new Watermark(35), 1);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// since channel 1 is still behind, channel 0 remains to be the only
// channel used to advance min watermark
valve.inputWatermark(new Watermark(37), 0);
assertEquals(new Watermark(37), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
// now, channel 1 has caught up with the overall min watermark
valve.inputWatermark(new Watermark(38), 1);
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
valve.inputWatermark(new Watermark(40), 0);
// this acknowledges that channel 1's watermark is being accounted for again
assertEquals(new Watermark(38), valveOutput.popLastOutputWatermark());
assertTrue(valveOutput.hasNoOutputWatermarks());
assertTrue(valveOutput.hasNoOutputStreamStatuses());
}
use of org.apache.flink.streaming.api.watermark.Watermark in project flink by apache.
the class WindowOperatorMigrationTest method testRestoreApplyEventTimeWindowsFromFlink11.
@Test
@SuppressWarnings("unchecked")
public void testRestoreApplyEventTimeWindowsFromFlink11() throws Exception {
final int WINDOW_SIZE = 3;
TypeInformation<Tuple2<String, Integer>> inputType = TypeInfoParser.parse("Tuple2<String, Integer>");
ListStateDescriptor<Tuple2<String, Integer>> stateDesc = new ListStateDescriptor<>("window-contents", inputType.createSerializer(new ExecutionConfig()));
WindowOperator<String, Tuple2<String, Integer>, Iterable<Tuple2<String, Integer>>, Tuple2<String, Integer>, TimeWindow> operator = new WindowOperator<>(TumblingEventTimeWindows.of(Time.of(WINDOW_SIZE, TimeUnit.SECONDS)), new TimeWindow.Serializer(), new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO.createSerializer(new ExecutionConfig()), stateDesc, new InternalIterableWindowFunction<>(new RichSumReducer<TimeWindow>()), EventTimeTrigger.create(), 0, null);
ConcurrentLinkedQueue<Object> expectedOutput = new ConcurrentLinkedQueue<>();
/*
operator.setInputType(TypeInfoParser.<Tuple2<String, Integer>>parse("Tuple2<String, Integer>"), new ExecutionConfig());
OneInputStreamOperatorTestHarness<Tuple2<String, Integer>, Tuple2<String, Integer>> testHarness =
new OneInputStreamOperatorTestHarness<>(operator);
testHarness.configureForKeyedStream(new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO);
testHarness.setup();
testHarness.open();
// add elements out-of-order
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 3999));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 3000));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key1", 1), 20));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key1", 1), 0));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key1", 1), 999));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 1998));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 1999));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 1000));
testHarness.processWatermark(new Watermark(999));
expectedOutput.add(new Watermark(999));
TestHarnessUtil.assertOutputEqualsSorted("Output was not correct.", expectedOutput, testHarness.getOutput(), new Tuple2ResultSortComparator());
testHarness.processWatermark(new Watermark(1999));
expectedOutput.add(new Watermark(1999));
TestHarnessUtil.assertOutputEqualsSorted("Output was not correct.", expectedOutput, testHarness.getOutput(), new Tuple2ResultSortComparator());
// do snapshot and save to file
StreamTaskState snapshot = testHarness.snapshot(0L, 0L);
testHarness.snaphotToFile(snapshot, "src/test/resources/win-op-migration-test-apply-event-time-flink1.1-snapshot");
testHarness.close();
*/
OneInputStreamOperatorTestHarness<Tuple2<String, Integer>, Tuple2<String, Integer>> testHarness = new KeyedOneInputStreamOperatorTestHarness<>(operator, new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO);
testHarness.setup();
testHarness.initializeStateFromLegacyCheckpoint(getResourceFilename("win-op-migration-test-apply-event-time-flink1.1-snapshot"));
testHarness.open();
testHarness.processWatermark(new Watermark(2999));
expectedOutput.add(new StreamRecord<>(new Tuple2<>("key1", 3), 2999));
expectedOutput.add(new StreamRecord<>(new Tuple2<>("key2", 3), 2999));
expectedOutput.add(new Watermark(2999));
testHarness.processWatermark(new Watermark(3999));
expectedOutput.add(new Watermark(3999));
testHarness.processWatermark(new Watermark(4999));
expectedOutput.add(new Watermark(4999));
testHarness.processWatermark(new Watermark(5999));
expectedOutput.add(new StreamRecord<>(new Tuple2<>("key2", 2), 5999));
expectedOutput.add(new Watermark(5999));
TestHarnessUtil.assertOutputEqualsSorted("Output was not correct.", expectedOutput, testHarness.getOutput(), new Tuple2ResultSortComparator());
testHarness.close();
}
use of org.apache.flink.streaming.api.watermark.Watermark in project flink by apache.
the class WindowOperatorTest method testCleanupTimeOverflow.
@Test
public void testCleanupTimeOverflow() throws Exception {
final int WINDOW_SIZE = 1000;
final long LATENESS = 2000;
TypeInformation<Tuple2<String, Integer>> inputType = TypeInfoParser.parse("Tuple2<String, Integer>");
ReducingStateDescriptor<Tuple2<String, Integer>> stateDesc = new ReducingStateDescriptor<>("window-contents", new SumReducer(), inputType.createSerializer(new ExecutionConfig()));
TumblingEventTimeWindows windowAssigner = TumblingEventTimeWindows.of(Time.milliseconds(WINDOW_SIZE));
final WindowOperator<String, Tuple2<String, Integer>, Tuple2<String, Integer>, Tuple2<String, Integer>, TimeWindow> operator = new WindowOperator<>(windowAssigner, new TimeWindow.Serializer(), new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO.createSerializer(new ExecutionConfig()), stateDesc, new InternalSingleValueWindowFunction<>(new PassThroughWindowFunction<String, TimeWindow, Tuple2<String, Integer>>()), EventTimeTrigger.create(), LATENESS, null);
OneInputStreamOperatorTestHarness<Tuple2<String, Integer>, Tuple2<String, Integer>> testHarness = new KeyedOneInputStreamOperatorTestHarness<>(operator, new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO);
testHarness.open();
ConcurrentLinkedQueue<Object> expected = new ConcurrentLinkedQueue<>();
long timestamp = Long.MAX_VALUE - 1750;
Collection<TimeWindow> windows = windowAssigner.assignWindows(new Tuple2<>("key2", 1), timestamp, new WindowAssigner.WindowAssignerContext() {
@Override
public long getCurrentProcessingTime() {
return operator.windowAssignerContext.getCurrentProcessingTime();
}
});
TimeWindow window = Iterables.getOnlyElement(windows);
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), timestamp));
// the garbage collection timer would wrap-around
Assert.assertTrue(window.maxTimestamp() + LATENESS < window.maxTimestamp());
// and it would prematurely fire with watermark (Long.MAX_VALUE - 1500)
Assert.assertTrue(window.maxTimestamp() + LATENESS < Long.MAX_VALUE - 1500);
// if we don't correctly prevent wrap-around in the garbage collection
// timers this watermark will clean our window state for the just-added
// element/window
testHarness.processWatermark(new Watermark(Long.MAX_VALUE - 1500));
// this watermark is before the end timestamp of our only window
Assert.assertTrue(Long.MAX_VALUE - 1500 < window.maxTimestamp());
Assert.assertTrue(window.maxTimestamp() < Long.MAX_VALUE);
// push in a watermark that will trigger computation of our window
testHarness.processWatermark(new Watermark(window.maxTimestamp()));
expected.add(new Watermark(Long.MAX_VALUE - 1500));
expected.add(new StreamRecord<>(new Tuple2<>("key2", 1), window.maxTimestamp()));
expected.add(new Watermark(window.maxTimestamp()));
TestHarnessUtil.assertOutputEqualsSorted("Output was not correct.", expected, testHarness.getOutput(), new Tuple2ResultSortComparator());
testHarness.close();
}
use of org.apache.flink.streaming.api.watermark.Watermark in project flink by apache.
the class WindowOperatorTest method testSideOutputDueToLatenessSessionZeroLateness.
@Test
public void testSideOutputDueToLatenessSessionZeroLateness() throws Exception {
final int GAP_SIZE = 3;
final long LATENESS = 0;
TypeInformation<Tuple2<String, Integer>> inputType = TypeInfoParser.parse("Tuple2<String, Integer>");
ReducingStateDescriptor<Tuple2<String, Integer>> stateDesc = new ReducingStateDescriptor<>("window-contents", new SumReducer(), inputType.createSerializer(new ExecutionConfig()));
WindowOperator<String, Tuple2<String, Integer>, Tuple2<String, Integer>, Tuple3<String, Long, Long>, TimeWindow> operator = new WindowOperator<>(EventTimeSessionWindows.withGap(Time.seconds(GAP_SIZE)), new TimeWindow.Serializer(), new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO.createSerializer(new ExecutionConfig()), stateDesc, new InternalSingleValueWindowFunction<>(new ReducedSessionWindowFunction()), EventTimeTrigger.create(), LATENESS, lateOutputTag);
OneInputStreamOperatorTestHarness<Tuple2<String, Integer>, Tuple3<String, Long, Long>> testHarness = new KeyedOneInputStreamOperatorTestHarness<>(operator, new TupleKeySelector(), BasicTypeInfo.STRING_TYPE_INFO);
testHarness.open();
ConcurrentLinkedQueue<Object> expected = new ConcurrentLinkedQueue<>();
ConcurrentLinkedQueue<Object> sideExpected = new ConcurrentLinkedQueue<>();
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 1000));
testHarness.processWatermark(new Watermark(1999));
expected.add(new Watermark(1999));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 2000));
testHarness.processWatermark(new Watermark(4998));
expected.add(new Watermark(4998));
// this will not be dropped because the session we're adding two has maxTimestamp
// after the current watermark
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 4500));
// new session
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 8500));
testHarness.processWatermark(new Watermark(7400));
expected.add(new Watermark(7400));
// this will merge the two sessions into one
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 7000));
testHarness.processWatermark(new Watermark(11501));
expected.add(new StreamRecord<>(new Tuple3<>("key2-5", 1000L, 11500L), 11499));
expected.add(new Watermark(11501));
// new session
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 11600));
testHarness.processWatermark(new Watermark(14600));
expected.add(new StreamRecord<>(new Tuple3<>("key2-1", 11600L, 14600L), 14599));
expected.add(new Watermark(14600));
// this is sideoutput as late, reuse last timestamp
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 10000));
sideExpected.add(new StreamRecord<>(new Tuple2<>("key2", 1), 10000));
testHarness.processElement(new StreamRecord<>(new Tuple2<>("key2", 1), 14500));
testHarness.processWatermark(new Watermark(20000));
expected.add(new StreamRecord<>(new Tuple3<>("key2-1", 14500L, 17500L), 17499));
expected.add(new Watermark(20000));
testHarness.processWatermark(new Watermark(100000));
expected.add(new Watermark(100000));
ConcurrentLinkedQueue<Object> actual = testHarness.getOutput();
ConcurrentLinkedQueue<StreamRecord<Tuple2<String, Integer>>> sideActual = testHarness.getSideOutput(lateOutputTag);
TestHarnessUtil.assertOutputEqualsSorted("Output was not correct.", expected, actual, new Tuple2ResultSortComparator());
TestHarnessUtil.assertOutputEqualsSorted("SideOutput was not correct.", sideExpected, (Iterable) sideActual, new Tuple2ResultSortComparator());
testHarness.close();
}
Aggregations