def test_query_structured_metrics(self):
mock_client, mock_job_result = self.setup_mock_client_result(
self.STRUCTURED_COUNTER_LIST)
dm = dataflow_metrics.DataflowMetrics(mock_client, mock_job_result)
dm._translate_step_name = types.MethodType(lambda self, x: 'split', dm)
query_result = dm.query()
expected_counters = [
MetricResult(
MetricKey(
'split',
MetricName('__main__.WordExtractingDoFn', 'word_lengths'),
), 109475, 109475),
]
self.assertEqual(query_result['counters'], expected_counters)
expected_distributions = [
MetricResult(
MetricKey(
'split',
MetricName('__main__.WordExtractingDoFn',
'word_length_dist'),
), DistributionResult(DistributionData(18, 2, 2, 16)),
DistributionResult(DistributionData(18, 2, 2, 16))),
]
self.assertEqual(query_result['distributions'], expected_distributions)
def test_direct_runner_metrics(self):
class MyDoFn(beam.DoFn):
def start_bundle(self):
count = Metrics.counter(self.__class__, 'bundles')
count.inc()
def finish_bundle(self):
count = Metrics.counter(self.__class__, 'finished_bundles')
count.inc()
def process(self, element):
gauge = Metrics.gauge(self.__class__, 'latest_element')
gauge.set(element)
count = Metrics.counter(self.__class__, 'elements')
count.inc()
distro = Metrics.distribution(self.__class__, 'element_dist')
distro.update(element)
return [element]
p = Pipeline(DirectRunner())
pcoll = (p | beam.Create([1, 2, 3, 4, 5])
| 'Do' >> beam.ParDo(MyDoFn()))
assert_that(pcoll, equal_to([1, 2, 3, 4, 5]))
result = p.run()
result.wait_until_finish()
metrics = result.metrics().query()
namespace = '{}.{}'.format(MyDoFn.__module__,
MyDoFn.__name__)
hc.assert_that(
metrics['counters'],
hc.contains_inanyorder(
MetricResult(
MetricKey('Do', MetricName(namespace, 'elements')),
5, 5),
MetricResult(
MetricKey('Do', MetricName(namespace, 'bundles')),
1, 1),
MetricResult(
MetricKey('Do', MetricName(namespace, 'finished_bundles')),
1, 1)))
hc.assert_that(
metrics['distributions'],
hc.contains_inanyorder(
MetricResult(
MetricKey('Do', MetricName(namespace, 'element_dist')),
DistributionResult(DistributionData(15, 5, 1, 5)),
DistributionResult(DistributionData(15, 5, 1, 5)))))
gauge_result = metrics['gauges'][0]
hc.assert_that(
gauge_result.key,
hc.equal_to(MetricKey('Do', MetricName(namespace, 'latest_element'))))
hc.assert_that(gauge_result.committed.value, hc.equal_to(5))
hc.assert_that(gauge_result.attempted.value, hc.equal_to(5))
def test_direct_runner_metrics(self):
from apache_beam.metrics.metric import Metrics
class MyDoFn(beam.DoFn):
def start_bundle(self):
count = Metrics.counter(self.__class__, 'bundles')
count.inc()
def finish_bundle(self):
count = Metrics.counter(self.__class__, 'finished_bundles')
count.inc()
def process(self, element):
count = Metrics.counter(self.__class__, 'elements')
count.inc()
distro = Metrics.distribution(self.__class__, 'element_dist')
distro.update(element)
return [element]
runner = DirectRunner()
p = Pipeline(runner,
options=PipelineOptions(self.default_properties))
# pylint: disable=expression-not-assigned
(p | ptransform.Create([1, 2, 3, 4, 5])
| 'Do' >> beam.ParDo(MyDoFn()))
result = p.run()
result.wait_until_finish()
metrics = result.metrics().query()
namespace = '{}.{}'.format(MyDoFn.__module__,
MyDoFn.__name__)
hc.assert_that(
metrics['counters'],
hc.contains_inanyorder(
MetricResult(
MetricKey('Do', MetricName(namespace, 'elements')),
5, 5),
MetricResult(
MetricKey('Do', MetricName(namespace, 'bundles')),
1, 1),
MetricResult(
MetricKey('Do', MetricName(namespace, 'finished_bundles')),
1, 1)))
hc.assert_that(
metrics['distributions'],
hc.contains_inanyorder(
MetricResult(
MetricKey('Do', MetricName(namespace, 'element_dist')),
DistributionResult(DistributionData(15, 5, 1, 5)),
DistributionResult(DistributionData(15, 5, 1, 5)))))
def _get_metric_value(self, metric):
"""Get a metric result object from a MetricUpdate from Dataflow API."""
if metric is None:
return None
if metric.scalar is not None:
return metric.scalar.integer_value
elif metric.distribution is not None:
dist_count = _get_match(
metric.distribution.object_value.properties,
lambda x: x.key == 'count').value.integer_value
dist_min = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'min').value.integer_value
dist_max = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'max').value.integer_value
dist_sum = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'sum').value.integer_value
if not dist_sum:
# distribution metric is not meant to use on large values, but in case
# it is, the value can overflow and become double_value, the correctness
# of the value may not be guaranteed.
_LOGGER.info(
"Distribution metric sum value seems to have "
"overflowed integer_value range, the correctness of sum or mean "
"value may not be guaranteed: %s" % metric.distribution)
dist_sum = int(
_get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'sum').value.double_value)
return DistributionResult(
DistributionData(dist_sum, dist_count, dist_min, dist_max))
else:
return None
def _get_metric_value(self, metric):
"""Get a metric result object from a MetricUpdate from Dataflow API."""
if metric is None:
return None
if metric.scalar is not None:
return metric.scalar.integer_value
elif metric.distribution is not None:
dist_count = _get_match(
metric.distribution.object_value.properties,
lambda x: x.key == 'count').value.integer_value
dist_min = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'min').value.integer_value
dist_max = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'max').value.integer_value
dist_mean = _get_match(
metric.distribution.object_value.properties,
lambda x: x.key == 'mean').value.integer_value
# Calculating dist_sum with a hack, as distribution sum is not yet
# available in the Dataflow API.
# TODO(pabloem) Switch to "sum" field once it's available in the API
dist_sum = dist_count * dist_mean
return DistributionResult(
DistributionData(dist_sum, dist_count, dist_min, dist_max))
else:
return None
def test_commit_logical_no_filter(self):
metrics = DirectMetrics()
metrics.commit_logical(
self.bundle1,
MetricUpdates(
counters={
MetricKey('step1', self.name1): 5,
MetricKey('step1', self.name2): 8
},
distributions={
MetricKey('step1', self.name1): DistributionData(8, 2, 3, 5)
}))
metrics.commit_logical(
self.bundle1,
MetricUpdates(
counters={
MetricKey('step2', self.name1): 7,
MetricKey('step1', self.name2): 4
},
distributions={
MetricKey('step1', self.name1): DistributionData(4, 1, 4, 4)
}))
results = metrics.query()
hc.assert_that(
results['counters'],
hc.contains_inanyorder(
*[
MetricResult(MetricKey('step1', self.name2), 12, 0),
MetricResult(MetricKey('step2', self.name1), 7, 0),
MetricResult(MetricKey('step1', self.name1), 5, 0)
]))
hc.assert_that(
results['distributions'],
hc.contains_inanyorder(
MetricResult(
MetricKey('step1', self.name1),
DistributionResult(DistributionData(12, 3, 3, 5)),
DistributionResult(DistributionData(0, 0, None, None)))))
def test_combiner_functions(self):
metrics = DirectMetrics()
counter = metrics._counters['anykey']
counter.commit_logical(self.bundle1, 5)
self.assertEqual(counter.extract_committed(), 5)
with self.assertRaises(TypeError):
counter.commit_logical(self.bundle1, None)
distribution = metrics._distributions['anykey']
distribution.commit_logical(self.bundle1, DistributionData(4, 1, 4, 4))
self.assertEqual(distribution.extract_committed(),
DistributionResult(DistributionData(4, 1, 4, 4)))
with self.assertRaises(AttributeError):
distribution.commit_logical(self.bundle1, None)
def extract_metric_result_map_value(monitoring_info_proto):
"""Returns the relevant GaugeResult, DistributionResult or int value.
These are the proper format for use in the MetricResult.query() result.
"""
# Returns a metric result (AKA the legacy format).
# from the MonitoringInfo
if is_counter(monitoring_info_proto):
return extract_counter_value(monitoring_info_proto)
if is_distribution(monitoring_info_proto):
(count, sum, min, max) = extract_distribution(monitoring_info_proto)
return DistributionResult(DistributionData(sum, count, min, max))
if is_gauge(monitoring_info_proto):
(timestamp, value) = extract_gauge_value(monitoring_info_proto)
return GaugeResult(GaugeData(value, timestamp))
def extract_metric_result_map_value(monitoring_info_proto):
"""Returns the relevant GaugeResult, DistributionResult or int value.
These are the proper format for use in the MetricResult.query() result.
"""
# Returns a metric result (AKA the legacy format).
# from the MonitoringInfo
if is_counter(monitoring_info_proto):
return extract_counter_value(monitoring_info_proto)
if is_distribution(monitoring_info_proto):
distribution_data = extract_distribution(monitoring_info_proto)
return DistributionResult(
DistributionData(distribution_data.sum, distribution_data.count,
distribution_data.min, distribution_data.max))
if is_gauge(monitoring_info_proto):
timestamp_secs = to_timestamp_secs(monitoring_info_proto.timestamp)
return GaugeResult(GaugeData(
extract_counter_value(monitoring_info_proto), timestamp_secs))
def _get_metric_value(self, metric):
"""Get a metric result object from a MetricUpdate from Dataflow API."""
if metric is None:
return None
if metric.scalar is not None:
return metric.scalar.integer_value
elif metric.distribution is not None:
dist_count = _get_match(
metric.distribution.object_value.properties,
lambda x: x.key == 'count').value.integer_value
dist_min = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'min').value.integer_value
dist_max = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'max').value.integer_value
dist_sum = _get_match(metric.distribution.object_value.properties,
lambda x: x.key == 'sum').value.integer_value
return DistributionResult(
DistributionData(dist_sum, dist_count, dist_min, dist_max))
else:
return None
def _create_metric_result(data_dict):
step = data_dict['step'] if 'step' in data_dict else ''
labels = data_dict['labels'] if 'labels' in data_dict else dict()
values = {}
for key in ['attempted', 'committed']:
if key in data_dict:
if 'counter' in data_dict[key]:
values[key] = data_dict[key]['counter']
elif 'distribution' in data_dict[key]:
distribution = data_dict[key]['distribution']
values[key] = DistributionResult(
DistributionData(
distribution['sum'],
distribution['count'],
distribution['min'],
distribution['max'],
))
attempted = values['attempted'] if 'attempted' in values else None
committed = values['committed'] if 'committed' in values else None
metric_name = MetricName(data_dict['namespace'], data_dict['name'])
metric_key = MetricKey(step, metric_name, labels)
return MetricResult(metric_key, committed, attempted)
def test_apply_physical_logical(self):
metrics = DirectMetrics()
dist_zero = DistributionData(0, 0, None, None)
metrics.update_physical(
object(),
MetricUpdates(counters={
MetricKey('step1', self.name1): 7,
MetricKey('step1', self.name2): 5,
MetricKey('step2', self.name1): 1
},
distributions={
MetricKey('step1', self.name1):
DistributionData(3, 1, 3, 3),
MetricKey('step2', self.name3):
DistributionData(8, 2, 4, 4)
}))
results = metrics.query()
hc.assert_that(
results['counters'],
hc.contains_inanyorder(*[
MetricResult(MetricKey('step1', self.name1), 0, 7),
MetricResult(MetricKey('step1', self.name2), 0, 5),
MetricResult(MetricKey('step2', self.name1), 0, 1)
]))
hc.assert_that(
results['distributions'],
hc.contains_inanyorder(*[
MetricResult(MetricKey('step1', self.name1),
DistributionResult(dist_zero),
DistributionResult(DistributionData(3, 1, 3, 3))),
MetricResult(MetricKey('step2', self.name3),
DistributionResult(dist_zero),
DistributionResult(DistributionData(8, 2, 4, 4)))
]))
metrics.commit_physical(
object(),
MetricUpdates(counters={
MetricKey('step1', self.name1): -3,
MetricKey('step2', self.name1): -5
},
distributions={
MetricKey('step1', self.name1):
DistributionData(8, 4, 1, 5),
MetricKey('step2', self.name2):
DistributionData(8, 8, 1, 1)
}))
results = metrics.query()
hc.assert_that(
results['counters'],
hc.contains_inanyorder(*[
MetricResult(MetricKey('step1', self.name1), 0, 4),
MetricResult(MetricKey('step1', self.name2), 0, 5),
MetricResult(MetricKey('step2', self.name1), 0, -4)
]))
hc.assert_that(
results['distributions'],
hc.contains_inanyorder(*[
MetricResult(MetricKey('step1', self.name1),
DistributionResult(dist_zero),
DistributionResult(DistributionData(11, 5, 1,
5))),
MetricResult(MetricKey('step2', self.name3),
DistributionResult(dist_zero),
DistributionResult(DistributionData(8, 2, 4, 4))),
MetricResult(MetricKey('step2', self.name2),
DistributionResult(dist_zero),
DistributionResult(DistributionData(8, 8, 1, 1)))
]))
metrics.commit_logical(
object(),
MetricUpdates(counters={
MetricKey('step1', self.name1): 3,
MetricKey('step1', self.name2): 5,
MetricKey('step2', self.name1): -3
},
distributions={
MetricKey('step1', self.name1):
DistributionData(11, 5, 1, 5),
MetricKey('step2', self.name2):
DistributionData(8, 8, 1, 1),
MetricKey('step2', self.name3):
DistributionData(4, 1, 4, 4)
}))
results = metrics.query()
hc.assert_that(
results['counters'],
hc.contains_inanyorder(*[
MetricResult(MetricKey('step1', self.name1), 3, 4),
MetricResult(MetricKey('step1', self.name2), 5, 5),
MetricResult(MetricKey('step2', self.name1), -3, -4)
]))
hc.assert_that(
results['distributions'],
hc.contains_inanyorder(*[
MetricResult(MetricKey('step1', self.name1),
DistributionResult(DistributionData(11, 5, 1, 5)),
DistributionResult(DistributionData(11, 5, 1,
5))),
MetricResult(MetricKey('step2', self.name3),
DistributionResult(DistributionData(4, 1, 4, 4)),
DistributionResult(DistributionData(8, 2, 4, 4))),
MetricResult(MetricKey('step2', self.name2),
DistributionResult(DistributionData(8, 8, 1, 1)),
DistributionResult(DistributionData(8, 8, 1, 1)))
]))