[
https://issues.apache.org/jira/browse/BEAM-7402?focusedWorklogId=259353&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-259353
]
ASF GitHub Bot logged work on BEAM-7402:
----------------------------------------
Author: ASF GitHub Bot
Created on: 13/Jun/19 08:09
Start Date: 13/Jun/19 08:09
Worklog Time Spent: 10m
Work Description: kamilwu commented on pull request #8675: [BEAM-7402]
BigQuery IO read performance tests
URL: https://github.com/apache/beam/pull/8675#discussion_r293253808
##########
File path: sdks/python/apache_beam/io/gcp/bigquery_read_perf_test.py
##########
@@ -0,0 +1,129 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+"""
+A performance test for reading data from a BigQuery table.
+Besides of the standard options, there are options with special meaning:
+* input_dataset - BQ dataset id.
+* input_table - BQ table id.
+The table will be created and populated with data from Synthetic Source if it
+does not exist.
+* input_options - options for Synthetic Source:
+num_records - number of rows to be inserted,
+value_size - the length of a single row,
+key_size - required option, but its value has no meaning.
+
+Example test run on DataflowRunner:
+
+python setup.py nosetests \
+ --test-pipeline-options="
+ --runner=TestDataflowRunner
+ --project=...
+ --staging_location=gs://...
+ --temp_location=gs://...
+ --sdk_location=.../dist/apache-beam-x.x.x.dev0.tar.gz
+ --input_dataset=...
+ --input_table=...
+ --input_options='{
+ \"num_records\": 1024,
+ \"key_size\": 1,
+ \"value_size\": 1024,
+ }'" \
+ --tests apache_beam.io.gcp.bigquery_read_perf_test
+"""
+
+from __future__ import absolute_import
+
+import base64
+import logging
+import os
+import unittest
+
+from apache_beam import Map
+from apache_beam.io import BigQueryDisposition
+from apache_beam.io import BigQuerySource
+from apache_beam.io import Read
+from apache_beam.io import WriteToBigQuery
+from apache_beam.io.gcp.bigquery_tools import BigQueryWrapper
+from apache_beam.io.gcp.bigquery_tools import parse_table_schema_from_json
+from apache_beam.testing.load_tests.load_test import LoadTest
+from apache_beam.testing.synthetic_pipeline import SyntheticSource
+from apache_beam.testing.test_pipeline import TestPipeline
+from apache_beam.testing.util import assert_that
+from apache_beam.testing.util import equal_to
+from apache_beam.transforms.combiners import Count
+
+load_test_enabled = False
+if os.environ.get('LOAD_TEST_ENABLED') == 'true':
+ load_test_enabled = True
+
+
[email protected](not load_test_enabled, 'Enabled only for phrase triggering.')
+class BigQueryReadPerfTest(LoadTest):
+ def setUp(self):
+ super(BigQueryReadPerfTest, self).setUp()
+ self.input_dataset = self.pipeline.get_option('input_dataset')
+ self.input_table = self.pipeline.get_option('input_table')
+ self._check_for_input_data()
+
+ def tearDown(self):
+ super(BigQueryReadPerfTest, self).tearDown()
+ assert_that(self.result, equal_to([self.input_options['num_records']]))
+
+ def _check_for_input_data(self):
+ """Checks if a BQ table with input data exists and creates it if not."""
+ wrapper = BigQueryWrapper()
+ try:
+ wrapper.get_table(self.project_id, self.input_dataset, self.input_table)
+ except Exception:
+ self._create_input_data()
Review comment:
Looks nice.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 259353)
Time Spent: 4h 20m (was: 4h 10m)
> Add a performance test for BigQueryIO read
> ------------------------------------------
>
> Key: BEAM-7402
> URL: https://issues.apache.org/jira/browse/BEAM-7402
> Project: Beam
> Issue Type: Test
> Components: testing
> Reporter: Kamil Wasilewski
> Assignee: Kamil Wasilewski
> Priority: Major
> Time Spent: 4h 20m
> Remaining Estimate: 0h
>
> The task is to add a performance test for BigQuery IO read with configurable
> data size.
> The plan is:
> 1) Setup BQ table with input data if needed,
> 2) Read data from that table and do some final assertions
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
