Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Shuffle coalesce read supports split-and-retry #11598

Open
wants to merge 3 commits into
base: branch-24.12
Choose a base branch
from
Open

Shuffle coalesce read supports split-and-retry #11598

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6f0b43d
Support split-retry for Shuffle coalesce read
firestarman Oct 10, 2024
df32c7e
Add tests
firestarman Oct 11, 2024
384576a
small fix
firestarman Oct 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions integration_tests/src/main/python/hash_aggregate_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1118,7 +1118,8 @@ def test_hash_groupby_typed_imperative_agg_without_gpu_implementation_fallback()
@disable_ansi_mode # https://github.com/NVIDIA/spark-rapids/issues/5114
@pytest.mark.parametrize('data_gen', _init_list, ids=idfn)
@pytest.mark.parametrize('conf', get_params(_confs, params_markers_for_confs), ids=idfn)
def test_hash_multiple_mode_query(data_gen, conf):
@pytest.mark.parametrize('shuffle_split', [True, False], ids=idfn)
def test_hash_multiple_mode_query(data_gen, conf, shuffle_split):
print_params(data_gen)
assert_gpu_and_cpu_are_equal_collect(
lambda spark: gen_df(spark, data_gen, length=100)
Expand All @@ -1132,7 +1133,10 @@ def test_hash_multiple_mode_query(data_gen, conf):
f.max('a'),
f.sumDistinct('b'),
f.countDistinct('c')
), conf=conf)
),
conf=copy_and_update(
conf,
{'spark.rapids.shuffle.splitRetryRead.enabled': shuffle_split}))


@approximate_float
Expand Down
8 changes: 6 additions & 2 deletions integration_tests/src/main/python/join_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,21 +242,25 @@ def test_hash_join_ridealong_non_sized(data_gen, join_type, sub_part_enabled):
@ignore_order(local=True)
@pytest.mark.parametrize('data_gen', basic_nested_gens + [decimal_gen_128bit], ids=idfn)
@pytest.mark.parametrize('join_type', all_symmetric_sized_join_types, ids=idfn)
@pytest.mark.parametrize('shuffle_split', [True, False], ids=idfn)
@allow_non_gpu(*non_utc_allow)
def test_hash_join_ridealong_symmetric(data_gen, join_type):
def test_hash_join_ridealong_symmetric(data_gen, join_type, shuffle_split):
confs = {
"spark.rapids.sql.join.useShuffledSymmetricHashJoin": "true",
"spark.rapids.shuffle.splitRetryRead.enabled": shuffle_split,
}
hash_join_ridealong(data_gen, join_type, confs)

@validate_execs_in_gpu_plan('GpuShuffledAsymmetricHashJoinExec')
@ignore_order(local=True)
@pytest.mark.parametrize('data_gen', basic_nested_gens + [decimal_gen_128bit], ids=idfn)
@pytest.mark.parametrize('join_type', all_asymmetric_sized_join_types, ids=idfn)
@pytest.mark.parametrize('shuffle_split', [True, False], ids=idfn)
@allow_non_gpu(*non_utc_allow)
def test_hash_join_ridealong_asymmetric(data_gen, join_type):
def test_hash_join_ridealong_asymmetric(data_gen, join_type, shuffle_split):
confs = {
"spark.rapids.sql.join.useShuffledAsymmetricHashJoin": "true",
"spark.rapids.shuffle.splitRetryRead.enabled": shuffle_split,
}
hash_join_ridealong(data_gen, join_type, confs)

Expand Down
Loading