You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by do...@apache.org on 2023/09/18 19:02:42 UTC
[spark] branch master updated: [SPARK-45153][BUILD][PS] Rebalance testing time for `pyspark-pandas-connect-part1`
This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 29acdf755cd [SPARK-45153][BUILD][PS] Rebalance testing time for `pyspark-pandas-connect-part1`
29acdf755cd is described below
commit 29acdf755cd0a5c88c5cc5c8c16947a5b8e840f9
Author: Haejoon Lee <ha...@databricks.com>
AuthorDate: Mon Sep 18 12:02:28 2023 -0700
[SPARK-45153][BUILD][PS] Rebalance testing time for `pyspark-pandas-connect-part1`
### What changes were proposed in this pull request?
This PR proposes to rebalance the tests for `pyspark-pandas-connect-part1`.
### Why are the changes needed?
We rebalance the CI by splitting slow tests into multiple parts, but `pyspark-pandas-connect-part1` takes almost an hour than other splitted `pyspark-pandas-connect-partx` tests as below:
|pyspark-pandas-connect-part0|pyspark-pandas-connect-part1|pyspark-pandas-connect-part2|
|--|--|--|
|1h 51m|2h 55m|1h 54m|
### Does this PR introduce _any_ user-facing change?
No, this PR is proposed to improve the build infra.
### How was this patch tested?
We should manually check the CI from GitHub Actions after PR is opened.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #42909 from itholic/SPARK-45153.
Authored-by: Haejoon Lee <ha...@databricks.com>
Signed-off-by: Dongjoon Hyun <dh...@apple.com>
---
.github/workflows/build_and_test.yml | 2 ++
dev/sparktestsupport/modules.py | 46 ++++++++++++++++++++++++------------
dev/sparktestsupport/utils.py | 14 +++++------
3 files changed, 40 insertions(+), 22 deletions(-)
diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml
index 9c5d25d30af..39fd2796015 100644
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -372,6 +372,8 @@ jobs:
pyspark-pandas-connect-part1
- >-
pyspark-pandas-connect-part2
+ - >-
+ pyspark-pandas-connect-part3
env:
MODULES_TO_TEST: ${{ matrix.modules }}
HADOOP_PROFILE: ${{ inputs.hadoop }}
diff --git a/dev/sparktestsupport/modules.py b/dev/sparktestsupport/modules.py
index 0a751052491..a3bfa288383 100644
--- a/dev/sparktestsupport/modules.py
+++ b/dev/sparktestsupport/modules.py
@@ -965,7 +965,6 @@ pyspark_pandas_connect_part0 = Module(
"pyspark.pandas.tests.connect.test_parity_utils",
"pyspark.pandas.tests.connect.test_parity_window",
"pyspark.pandas.tests.connect.indexes.test_parity_base",
- "pyspark.pandas.tests.connect.indexes.test_parity_datetime",
"pyspark.pandas.tests.connect.indexes.test_parity_align",
"pyspark.pandas.tests.connect.indexes.test_parity_indexing",
"pyspark.pandas.tests.connect.indexes.test_parity_reindex",
@@ -982,7 +981,10 @@ pyspark_pandas_connect_part0 = Module(
"pyspark.pandas.tests.connect.computation.test_parity_describe",
"pyspark.pandas.tests.connect.computation.test_parity_eval",
"pyspark.pandas.tests.connect.computation.test_parity_melt",
- "pyspark.pandas.tests.connect.computation.test_parity_pivot",
+ "pyspark.pandas.tests.connect.groupby.test_parity_stat",
+ "pyspark.pandas.tests.connect.frame.test_parity_attrs",
+ "pyspark.pandas.tests.connect.diff_frames_ops.test_parity_dot_frame",
+ "pyspark.pandas.tests.connect.diff_frames_ops.test_parity_dot_series",
],
excluded_python_implementations=[
"PyPy" # Skip these tests under PyPy since they require numpy, pandas, and pyarrow and
@@ -999,7 +1001,6 @@ pyspark_pandas_connect_part1 = Module(
],
python_test_goals=[
# pandas-on-Spark unittests
- "pyspark.pandas.tests.connect.frame.test_parity_attrs",
"pyspark.pandas.tests.connect.frame.test_parity_constructor",
"pyspark.pandas.tests.connect.frame.test_parity_conversion",
"pyspark.pandas.tests.connect.frame.test_parity_reindexing",
@@ -1012,21 +1013,12 @@ pyspark_pandas_connect_part1 = Module(
"pyspark.pandas.tests.connect.groupby.test_parity_aggregate",
"pyspark.pandas.tests.connect.groupby.test_parity_apply_func",
"pyspark.pandas.tests.connect.groupby.test_parity_cumulative",
- "pyspark.pandas.tests.connect.groupby.test_parity_describe",
- "pyspark.pandas.tests.connect.groupby.test_parity_groupby",
- "pyspark.pandas.tests.connect.groupby.test_parity_head_tail",
- "pyspark.pandas.tests.connect.groupby.test_parity_index",
"pyspark.pandas.tests.connect.groupby.test_parity_missing_data",
"pyspark.pandas.tests.connect.groupby.test_parity_split_apply",
- "pyspark.pandas.tests.connect.groupby.test_parity_stat",
"pyspark.pandas.tests.connect.test_parity_indexing",
- "pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames",
- "pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames_groupby",
"pyspark.pandas.tests.connect.diff_frames_ops.test_parity_align",
"pyspark.pandas.tests.connect.diff_frames_ops.test_parity_basic_slow",
"pyspark.pandas.tests.connect.diff_frames_ops.test_parity_cov_corrwith",
- "pyspark.pandas.tests.connect.diff_frames_ops.test_parity_dot_frame",
- "pyspark.pandas.tests.connect.diff_frames_ops.test_parity_dot_series",
"pyspark.pandas.tests.connect.diff_frames_ops.test_parity_index",
"pyspark.pandas.tests.connect.diff_frames_ops.test_parity_series",
"pyspark.pandas.tests.connect.diff_frames_ops.test_parity_setitem_frame",
@@ -1043,7 +1035,10 @@ pyspark_pandas_connect_part1 = Module(
"pyspark.pandas.tests.connect.series.test_parity_series",
"pyspark.pandas.tests.connect.series.test_parity_sort",
"pyspark.pandas.tests.connect.series.test_parity_stat",
+ "pyspark.pandas.tests.connect.data_type_ops.test_parity_num_arithmetic",
+ "pyspark.pandas.tests.connect.test_parity_reshape",
"pyspark.pandas.tests.connect.test_parity_stats",
+ "pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames_groupby_expanding",
],
excluded_python_implementations=[
"PyPy" # Skip these tests under PyPy since they require numpy, pandas, and pyarrow and
@@ -1060,20 +1055,41 @@ pyspark_pandas_connect_part2 = Module(
],
python_test_goals=[
# pandas-on-Spark unittests
+ "pyspark.pandas.tests.connect.computation.test_parity_pivot",
"pyspark.pandas.tests.connect.indexes.test_parity_base_slow",
"pyspark.pandas.tests.connect.indexes.test_parity_datetime_property",
"pyspark.pandas.tests.connect.test_parity_frame_interpolate",
"pyspark.pandas.tests.connect.test_parity_series_interpolate",
"pyspark.pandas.tests.connect.test_parity_frame_resample",
"pyspark.pandas.tests.connect.test_parity_series_resample",
- "pyspark.pandas.tests.connect.test_parity_reshape",
- "pyspark.pandas.tests.connect.data_type_ops.test_parity_num_arithmetic",
"pyspark.pandas.tests.connect.test_parity_ewm",
"pyspark.pandas.tests.connect.test_parity_rolling",
"pyspark.pandas.tests.connect.test_parity_expanding",
- "pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames_groupby_expanding",
"pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames_groupby_rolling",
"pyspark.pandas.tests.connect.computation.test_parity_missing_data",
+ "pyspark.pandas.tests.connect.groupby.test_parity_index",
+ "pyspark.pandas.tests.connect.groupby.test_parity_describe",
+ "pyspark.pandas.tests.connect.groupby.test_parity_head_tail",
+ "pyspark.pandas.tests.connect.groupby.test_parity_groupby",
+ ],
+ excluded_python_implementations=[
+ "PyPy" # Skip these tests under PyPy since they require numpy, pandas, and pyarrow and
+ # they aren't available there
+ ],
+)
+
+
+pyspark_pandas_connect_part3 = Module(
+ name="pyspark-pandas-connect-part3",
+ dependencies=[pyspark_connect, pyspark_pandas, pyspark_pandas_slow],
+ source_file_regexes=[
+ "python/pyspark/pandas",
+ ],
+ python_test_goals=[
+ # pandas-on-Spark unittests
+ "pyspark.pandas.tests.connect.indexes.test_parity_datetime",
+ "pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames",
+ "pyspark.pandas.tests.connect.test_parity_ops_on_diff_frames_groupby",
],
excluded_python_implementations=[
"PyPy" # Skip these tests under PyPy since they require numpy, pandas, and pyarrow and
diff --git a/dev/sparktestsupport/utils.py b/dev/sparktestsupport/utils.py
index c21ab7b384a..441ae3cf8be 100755
--- a/dev/sparktestsupport/utils.py
+++ b/dev/sparktestsupport/utils.py
@@ -114,16 +114,16 @@ def determine_modules_to_test(changed_modules, deduplicated=True):
['avro', 'connect', 'docker-integration-tests', 'examples', 'hive', 'hive-thriftserver',
'mllib', 'protobuf', 'pyspark-connect', 'pyspark-ml', 'pyspark-ml-connect', 'pyspark-mllib',
'pyspark-pandas', 'pyspark-pandas-connect-part0', 'pyspark-pandas-connect-part1',
- 'pyspark-pandas-connect-part2', 'pyspark-pandas-slow', 'pyspark-sql', 'pyspark-testing',
- 'repl', 'sparkr', 'sql', 'sql-kafka-0-10']
+ 'pyspark-pandas-connect-part2', 'pyspark-pandas-connect-part3', 'pyspark-pandas-slow',
+ 'pyspark-sql', 'pyspark-testing', 'repl', 'sparkr', 'sql', 'sql-kafka-0-10']
>>> sorted([x.name for x in determine_modules_to_test(
... [modules.sparkr, modules.sql], deduplicated=False)])
... # doctest: +NORMALIZE_WHITESPACE
['avro', 'connect', 'docker-integration-tests', 'examples', 'hive', 'hive-thriftserver',
'mllib', 'protobuf', 'pyspark-connect', 'pyspark-ml', 'pyspark-ml-connect', 'pyspark-mllib',
'pyspark-pandas', 'pyspark-pandas-connect-part0', 'pyspark-pandas-connect-part1',
- 'pyspark-pandas-connect-part2', 'pyspark-pandas-slow', 'pyspark-sql', 'pyspark-testing',
- 'repl', 'sparkr', 'sql', 'sql-kafka-0-10']
+ 'pyspark-pandas-connect-part2', 'pyspark-pandas-connect-part3', 'pyspark-pandas-slow',
+ 'pyspark-sql', 'pyspark-testing', 'repl', 'sparkr', 'sql', 'sql-kafka-0-10']
>>> sorted([x.name for x in determine_modules_to_test(
... [modules.sql, modules.core], deduplicated=False)])
... # doctest: +NORMALIZE_WHITESPACE
@@ -131,9 +131,9 @@ def determine_modules_to_test(changed_modules, deduplicated=True):
'hive', 'hive-thriftserver', 'mllib', 'mllib-local', 'protobuf', 'pyspark-connect',
'pyspark-core', 'pyspark-ml', 'pyspark-ml-connect', 'pyspark-mllib', 'pyspark-pandas',
'pyspark-pandas-connect-part0', 'pyspark-pandas-connect-part1', 'pyspark-pandas-connect-part2',
- 'pyspark-pandas-slow', 'pyspark-resource', 'pyspark-sql', 'pyspark-streaming',
- 'pyspark-testing', 'repl', 'root', 'sparkr', 'sql', 'sql-kafka-0-10', 'streaming',
- 'streaming-kafka-0-10', 'streaming-kinesis-asl']
+ 'pyspark-pandas-connect-part3', 'pyspark-pandas-slow', 'pyspark-resource', 'pyspark-sql',
+ 'pyspark-streaming', 'pyspark-testing', 'repl', 'root', 'sparkr', 'sql', 'sql-kafka-0-10',
+ 'streaming', 'streaming-kafka-0-10', 'streaming-kinesis-asl']
"""
modules_to_test = set()
for module in changed_modules:
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org