[ https://issues.apache.org/jira/browse/BEAM-9085?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17027900#comment-17027900 ]
Valentyn Tymofieiev commented on BEAM-9085: ------------------------------------------- It appears that the increase in time is likely caused by either generating the synthetic input, or reading the synthetic input. The problem can be reproduced on Direct runner as well, I don't think it's Dataflow-specific. Following command shows 14 (Py2) vs 40 (Py3) seconds difference on my machine. {noformat} python setup.py nosetests \ --test-pipeline-options=" --iterations=10 --number_of_counters=1 --number_of_counter_operations=1 --project=big-query-project --publish_to_big_query=false --metrics_dataset=python_load_tests --metrics_table=pardo --input_options='{ \"num_records\": 200000, \"key_size\": 10, \"value_size\":90, \"bundle_size_distribution_type\": \"const\", \"bundle_size_distribution_param\": 1, \"force_initial_num_bundles\": 0 }'" \ --tests apache_beam.testing.load_tests.pardo_test {noformat} > Investigate performance difference between Python 2/3 on Dataflow > ----------------------------------------------------------------- > > Key: BEAM-9085 > URL: https://issues.apache.org/jira/browse/BEAM-9085 > Project: Beam > Issue Type: Bug > Components: sdk-py-core > Reporter: Kamil Wasilewski > Assignee: Valentyn Tymofieiev > Priority: Major > > Tests show that the performance of core Beam operations in Python 3.x on > Dataflow can be a few time slower than in Python 2.7. We should investigate > what's the cause of the problem. > Currently, we have one ParDo test that is run both in Py3 and Py2 [1]. A > dashboard with runtime results can be found here [2]. > [1] sdks/python/apache_beam/testing/load_tests/pardo_test.py > [2] https://apache-beam-testing.appspot.com/explore?dashboard=5678187241537536 -- This message was sent by Atlassian Jira (v8.3.4#803005)