パイプラインのトラブルシューティングとデバッグ

...
... Exception in thread "main" java.lang.IllegalStateException:
... GroupByKey cannot be applied to non-bounded PCollection in the GlobalWindow without a trigger.
... Use a Window.into or Window.triggering transform prior to GroupByKey
...

... in <module> run()
... in run | beam.Map('count', lambda (word, ones): (word, sum(ones))))
... in __or__ return self.pipeline.apply(ptransform, self)
... in apply transform.type_check_inputs(pvalueish)
... in type_check_inputs self.type_check_inputs_or_outputs(pvalueish, 'input')
... in type_check_inputs_or_outputs pvalue_.element_type))
google.cloud.dataflow.typehints.decorators.TypeCheckError: Input type hint violation at group: expected Tuple[TypeVariable[K], TypeVariable[V]], got <type 'str'>

... panic: Method ProcessElement in DoFn main.extractFn is missing all inputs. A main input is required.
... Full error:
...     inserting ParDo in scope root/CountWords
...     graph.AsDoFn: for Fn named main.extractFn
... ProcessElement method has no main inputs

... goroutine 1 [running]:
... github.com/apache/beam/sdks/v2/go/pkg/beam.MustN(...)
... (more stacktrace)

INFO: To access the Dataflow monitoring console, please navigate to
  https://console.developers.google.com/project/google.com%3Aclouddfe/dataflow/job/2016-03-08_18_59_25-16868399470801620798
Submitted job: 2016-03-08_18_59_25-16868399470801620798
...
... Starting 3 workers...
... Executing operation BigQuery-Read+AnonymousParDo+BigQuery-Write
... Executing BigQuery import job "dataflow_job_16868399470801619475".
... Stopping worker pool...
... Workflow failed. Causes: ...BigQuery-Read+AnonymousParDo+BigQuery-Write failed.
Causes: ... BigQuery getting table "non_existent_table" from dataset "cws_demo" in project "my_project" failed.
Message: Not found: Table x:cws_demo.non_existent_table HTTP Code: 404
... Worker pool stopped.
... com.google.cloud.dataflow.sdk.runners.BlockingDataflowPipelineRunner run
INFO: Job finished with status FAILED
Exception in thread "main" com.google.cloud.dataflow.sdk.runners.DataflowJobExecutionException:
  Job 2016-03-08_18_59_25-16868399470801620798 failed with status FAILED
    at com.google.cloud.dataflow.sdk.runners.DataflowRunner.run(DataflowRunner.java:155)
    at com.google.cloud.dataflow.sdk.runners.DataflowRunner.run(DataflowRunner.java:56)
    at com.google.cloud.dataflow.sdk.Pipeline.run(Pipeline.java:180)
    at com.google.cloud.dataflow.integration.BigQueryCopyTableExample.main(BigQueryCopyTableExample.java:74)

INFO:root:Created job with id: [2016-03-08_14_12_01-2117248033993412477]
... Checking required Cloud APIs are enabled.
... Job 2016-03-08_14_12_01-2117248033993412477 is in state JOB_STATE_RUNNING.
... Combiner lifting skipped for step group: GroupByKey not followed by a combiner.
... Expanding GroupByKey operations into optimizable parts.
... Lifting ValueCombiningMappingFns into MergeBucketsMappingFns
... Annotating graph with Autotuner information.
... Fusing adjacent ParDo, Read, Write, and Flatten operations
... Fusing consumer split into read
...
... Starting 1 workers...
...
... Executing operation read+split+pair_with_one+group/Reify+group/Write
... Executing failure step failure14
... Workflow failed.
Causes: ... read+split+pair_with_one+group/Reify+group/Write failed.
Causes: ... Unable to view metadata for files: gs://dataflow-samples/shakespeare/missing.txt.
... Cleaning up.
... Tearing down pending resources...
INFO:root:Job 2016-03-08_14_12_01-2117248033993412477 is in state JOB_STATE_FAILED.

INFO: To access the Dataflow monitoring console, please navigate to https://console.developers.google.com/project/example_project/dataflow/job/2017-05-23_14_02_46-1117850763061203461
Submitted job: 2017-05-23_14_02_46-1117850763061203461
...
... To cancel the job using the 'gcloud' tool, run: gcloud beta dataflow jobs --project=example_project cancel 2017-05-23_14_02_46-1117850763061203461
... Autoscaling is enabled for job 2017-05-23_14_02_46-1117850763061203461.
... The number of workers will be between 1 and 15.
... Autoscaling was automatically enabled for job 2017-05-23_14_02_46-1117850763061203461.
...
... Executing operation BigQueryIO.Write/BatchLoads/Create/Read(CreateSource)+BigQueryIO.Write/BatchLoads/GetTempFilePrefix+BigQueryIO.Write/BatchLoads/TempFilePrefixView/BatchViewOverrides.GroupByWindowHashAsKeyAndWindowAsSortKey/ParDo(UseWindowHashAsKeyAndWindowAsSortKey)+BigQueryIO.Write/BatchLoads/TempFilePrefixView/Combine.GloballyAsSingletonView/Combine.globally(Singleton)/WithKeys/AddKeys/Map/ParMultiDo(Anonymous)+BigQueryIO.Write/BatchLoads/TempFilePrefixView/Combine.GloballyAsSingletonView/Combine.globally(Singleton)/Combine.perKey(Singleton)/GroupByKey/Reify+BigQueryIO.Write/BatchLoads/TempFilePrefixView/Combine.GloballyAsSingletonView/Combine.globally(Singleton)/Combine.perKey(Singleton)/GroupByKey/Write+BigQueryIO.Write/BatchLoads/TempFilePrefixView/BatchViewOverrides.GroupByWindowHashAsKeyAndWindowAsSortKey/BatchViewOverrides.GroupByKeyAndSortValuesOnly/Write
... Workers have started successfully.
...
... org.apache.beam.runners.dataflow.util.MonitoringUtil$LoggingHandler process SEVERE: 2017-05-23T21:06:33.711Z: (c14bab21d699a182): java.lang.RuntimeException: org.apache.beam.sdk.util.UserCodeException: java.lang.ArithmeticException: / by zero
        at com.google.cloud.dataflow.worker.runners.worker.GroupAlsoByWindowsParDoFn$1.output(GroupAlsoByWindowsParDoFn.java:146)
        at com.google.cloud.dataflow.worker.runners.worker.GroupAlsoByWindowFnRunner$1.outputWindowedValue(GroupAlsoByWindowFnRunner.java:104)
        at com.google.cloud.dataflow.worker.util.BatchGroupAlsoByWindowAndCombineFn.closeWindow(BatchGroupAlsoByWindowAndCombineFn.java:191)
...
... Cleaning up.
... Stopping worker pool...
... Worker pool stopped.

INFO:root:Job 2016-03-08_14_21_32-8974754969325215880 is in state JOB_STATE_RUNNING.
...
INFO:root:... Expanding GroupByKey operations into optimizable parts.
INFO:root:... Lifting ValueCombiningMappingFns into MergeBucketsMappingFns
INFO:root:... Annotating graph with Autotuner information.
INFO:root:... Fusing adjacent ParDo, Read, Write, and Flatten operations
...
INFO:root:...: Starting 1 workers...
INFO:root:...: Executing operation group/Create
INFO:root:...: Value "group/Session" materialized.
INFO:root:...: Executing operation read+split+pair_with_one+group/Reify+group/Write
INFO:root:Job 2016-03-08_14_21_32-8974754969325215880 is in state JOB_STATE_RUNNING.
INFO:root:...: ...: Workers have started successfully.
INFO:root:Job 2016-03-08_14_21_32-8974754969325215880 is in state JOB_STATE_RUNNING.
INFO:root:...: Traceback (most recent call last):
  File ".../dataflow_worker/batchworker.py", line 384, in do_work self.current_executor.execute(work_item.map_task)
  ...
  File ".../apache_beam/examples/wordcount.runfiles/py/apache_beam/examples/wordcount.py", line 73, in <lambda>
ValueError: invalid literal for int() with base 10: 'www'

... 2022-05-26T18:32:52.752315397Zprocess bundle failed for instruction
...     process_bundle-4031463614776698457-2 using plan s02-6 : while executing
...     Process for Plan[s02-6] failed: Oh no! This is an error message!

final Counter counter = Metrics.counter("stats", "even-items");
PCollection<Integer> input = pipeline.apply(...);
...
input.apply(ParDo.of(new DoFn<Integer, Integer>() {
  @ProcessElement
  public void processElement(ProcessContext c) {
    if (c.element() % 2 == 0) {
      counter.inc();
    }
});

class FilterTextFn(beam.DoFn):
      """A DoFn that filters for a specific key based on a regex."""

      def __init__(self, pattern):
        self.pattern = pattern
        # A custom metric can track values in your pipeline as it runs. Create
        # custom metrics to count unmatched words, and know the distribution of
        # word lengths in the input PCollection.
        self.word_len_dist = Metrics.distribution(self.__class__,
                                                  'word_len_dist')
        self.unmatched_words = Metrics.counter(self.__class__,
                                               'unmatched_words')

      def process(self, element):
        word = element
        self.word_len_dist.update(len(word))
        if re.match(self.pattern, word):
          yield element
        else:
          self.unmatched_words.inc()

    filtered_words = (
        words | 'FilterText' >> beam.ParDo(FilterTextFn('s.*')))

func addMetricDoFnToPipeline(s beam.Scope, input beam.PCollection) beam.PCollection {
    return beam.ParDo(s, &MyMetricsDoFn{}, input)
}

func executePipelineAndGetMetrics(ctx context.Context, p *beam.Pipeline) (metrics.QueryResults, error) {
    pr, err := beam.Run(ctx, runner, p)
    if err != nil {
        return metrics.QueryResults{}, err
    }

    // Request the metric called "counter1" in namespace called "namespace"
    ms := pr.Metrics().Query(func(r beam.MetricResult) bool {
        return r.Namespace() == "namespace" && r.Name() == "counter1"
    })

    // Print the metric value - there should be only one line because there is
    // only one metric called "counter1" in the namespace called "namespace"
    for _, c := range ms.Counters() {
        fmt.Println(c.Namespace(), "-", c.Name(), ":", c.Committed)
    }
    return ms, nil
}

type MyMetricsDoFn struct {
    counter beam.Counter
}

func init() {
    beam.RegisterType(reflect.TypeOf((*MyMetricsDoFn)(nil)))
}

func (fn *MyMetricsDoFn) Setup() {
    // While metrics can be defined in package scope or dynamically
    // it's most efficient to include them in the DoFn.
    fn.counter = beam.NewCounter("namespace", "counter1")
}

func (fn *MyMetricsDoFn) ProcessElement(ctx context.Context, v beam.V, emit func(beam.V)) {
    // count the elements
    fn.counter.Inc(ctx, 1)
    emit(v)
}