github.com/apache/beam/sdks/v2@v2.48.2/python/apache_beam/tools/sideinput_microbenchmark.py (about)

     1  # Licensed to the Apache Software Foundation (ASF) under one or more
     2  # contributor license agreements.  See the NOTICE file distributed with
     3  # this work for additional information regarding copyright ownership.
     4  # The ASF licenses this file to You under the Apache License, Version 2.0
     5  # (the "License"); you may not use this file except in compliance with
     6  # the License.  You may obtain a copy of the License at
     7  #
     8  #    http://www.apache.org/licenses/LICENSE-2.0
     9  #
    10  # Unless required by applicable law or agreed to in writing, software
    11  # distributed under the License is distributed on an "AS IS" BASIS,
    12  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    13  # See the License for the specific language governing permissions and
    14  # limitations under the License.
    15  #
    16  
    17  """A microbenchmark for measuring performance of Side Inputs iterable.
    18  
    19  Runs side input iterable that fetches from multiple FakeSources, and
    20  measures the time to fetch all elements from all sources.
    21  
    22  Run as
    23    python -m apache_beam.tools.sideinput_microbenchmark
    24  """
    25  
    26  # pytype: skip-file
    27  
    28  import logging
    29  import time
    30  
    31  from apache_beam.runners.worker import opcounters
    32  from apache_beam.runners.worker import sideinputs
    33  from apache_beam.runners.worker import statesampler
    34  from apache_beam.runners.worker.sideinputs_test import FakeSource
    35  from apache_beam.tools import utils
    36  from apache_beam.utils.counters import CounterFactory
    37  
    38  
    39  def long_generator(value, elements):
    40    for _ in range(elements):
    41      yield value
    42  
    43  
    44  def run_benchmark(num_runs=50, input_per_source=4000, num_sources=4):
    45    print("Number of runs:", num_runs)
    46    print("Input size:", num_sources * input_per_source)
    47    print("Sources:", num_sources)
    48  
    49    times = []
    50    for _ in range(num_runs):
    51      counter_factory = CounterFactory()
    52      state_sampler = statesampler.StateSampler('basic', counter_factory)
    53      state_sampler.start()
    54      with state_sampler.scoped_state('step1', 'state'):
    55        si_counter = opcounters.SideInputReadCounter(
    56            counter_factory, state_sampler, 'step1', 1)
    57        si_counter = opcounters.NoOpTransformIOCounter()
    58        sources = [
    59            FakeSource(long_generator(i, input_per_source))
    60            for i in range(num_sources)
    61        ]
    62        iterator_fn = sideinputs.get_iterator_fn_for_sources(
    63            sources, read_counter=si_counter)
    64        start = time.time()
    65        list(iterator_fn())
    66        time_cost = time.time() - start
    67        times.append(time_cost)
    68      state_sampler.stop()
    69  
    70    print("Runtimes:", times)
    71  
    72    avg_runtime = sum(times) / len(times)
    73    print("Average runtime:", avg_runtime)
    74    print("Time per element:", avg_runtime / (input_per_source * num_sources))
    75  
    76  
    77  if __name__ == '__main__':
    78    logging.basicConfig()
    79    utils.check_compiled('apache_beam.runners.worker.opcounters')
    80    run_benchmark()