mirror of
https://github.com/apache/impala.git
synced 2025-12-19 18:12:08 -05:00
f98b697c7b
This change adds get_workload() to ImpalaTestSuite and removes it from all test suites that already returned 'functional-query'. get_workload() is also removed from CustomClusterTestSuite which used to return 'tpch'. All other changes besides impala_test_suite.py and custom_cluster_test_suite.py are just mass removals of get_workload() functions. The behavior is only changed in custom cluster tests that didn't override get_workload(). By returning 'functional-query' instead of 'tpch', exploration_strategy() will no longer return 'core' in 'exhaustive' test runs. See IMPALA-3947 on why workload affected exploration_strategy. An example for affected test is TestCatalogHMSFailures which was skipped both in core and exhaustive runs before this change. get_workload() functions that return a different workload than 'functional-query' are not changed - it is possible that some of these also don't handle exploration_strategy() as expected, but individually checking these tests is out of scope in this patch. Change-Id: I9ec6c41ffb3a30e1ea2de773626d1485c69fe115 Reviewed-on: http://gerrit.cloudera.org:8080/22726 Reviewed-by: Riza Suminto <riza.suminto@cloudera.com> Reviewed-by: Daniel Becker <daniel.becker@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
119 lines
6.0 KiB
Python
119 lines
6.0 KiB
Python
# 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.
|
|
|
|
from __future__ import absolute_import, division, print_function
|
|
from copy import deepcopy
|
|
|
|
from tests.common.file_utils import (
|
|
create_table_from_parquet, create_table_and_copy_files)
|
|
from tests.common.test_dimensions import (
|
|
add_exec_option_dimension,
|
|
create_exec_option_dimension)
|
|
from tests.common.impala_test_suite import ImpalaTestSuite
|
|
|
|
MT_DOP_VALUES = [0, 1, 2, 8]
|
|
|
|
|
|
class TestParquetStatsSingleNode(ImpalaTestSuite):
|
|
"""
|
|
This suite tests runtime optimizations based on Parquet statistics with num_nodes=1.
|
|
"""
|
|
|
|
@classmethod
|
|
def add_test_dimensions(cls):
|
|
super(TestParquetStatsSingleNode, cls).add_test_dimensions()
|
|
cls.ImpalaTestMatrix.add_dimension(create_exec_option_dimension(cluster_sizes=[1]))
|
|
add_exec_option_dimension(cls, 'mt_dop', MT_DOP_VALUES)
|
|
cls.ImpalaTestMatrix.add_constraint(
|
|
lambda v: v.get_value('table_format').file_format == 'parquet')
|
|
|
|
def test_parquet_stats(self, vector, unique_database):
|
|
# The test makes assumptions about the number of row groups that are processed and
|
|
# skipped inside a fragment, so we ensure that the tests run in a single fragment.
|
|
self.run_test_case('QueryTest/parquet-stats', vector, use_db=unique_database)
|
|
|
|
def test_deprecated_stats(self, vector, unique_database):
|
|
"""Test that reading parquet files with statistics with deprecated 'min'/'max' fields
|
|
works correctly. The statistics will be used for known-good types (boolean, integral,
|
|
float) and will be ignored for all other types (string, decimal, timestamp)."""
|
|
|
|
# We use CTAS instead of "create table like" to convert the partition columns into
|
|
# normal table columns.
|
|
create_table_and_copy_files(self.client, 'create table {db}.{tbl} stored as parquet '
|
|
'as select * from functional.alltypessmall '
|
|
'limit 0',
|
|
unique_database, 'deprecated_stats',
|
|
['testdata/data/deprecated_statistics.parquet'])
|
|
# The test makes assumptions about the number of row groups that are processed and
|
|
# skipped inside a fragment, so we ensure that the tests run in a single fragment.
|
|
self.run_test_case('QueryTest/parquet-deprecated-stats', vector, unique_database)
|
|
|
|
|
|
class TestParquetStats(ImpalaTestSuite):
|
|
"""
|
|
This suite tests runtime optimizations based on Parquet statistics.
|
|
"""
|
|
|
|
@classmethod
|
|
def add_test_dimensions(cls):
|
|
super(TestParquetStats, cls).add_test_dimensions()
|
|
# Fix batch_size to the default value.
|
|
cls.ImpalaTestMatrix.add_dimension(create_exec_option_dimension(batch_sizes=[0]))
|
|
add_exec_option_dimension(cls, 'mt_dop', MT_DOP_VALUES)
|
|
cls.ImpalaTestMatrix.add_constraint(
|
|
lambda v: v.get_value('table_format').file_format == 'parquet')
|
|
|
|
def test_invalid_stats(self, vector, unique_database):
|
|
"""IMPALA-6538" Test that reading parquet files with statistics with invalid
|
|
'min_value'/'max_value' fields works correctly. 'min_value' and 'max_value' are both
|
|
NaNs, therefore we need to ignore them"""
|
|
create_table_from_parquet(self.client, unique_database, 'min_max_is_nan')
|
|
self.run_test_case('QueryTest/parquet-invalid-minmax-stats', vector, unique_database)
|
|
|
|
def test_page_index(self, vector, unique_database):
|
|
"""Test that using the Parquet page index works well. The various test files
|
|
contain queries that exercise the page selection and value-skipping logic against
|
|
columns with different types and encodings."""
|
|
new_vector = deepcopy(vector)
|
|
del new_vector.get_value('exec_option')['abort_on_error']
|
|
create_table_from_parquet(self.client, unique_database, 'decimals_1_10')
|
|
create_table_from_parquet(self.client, unique_database, 'nested_decimals')
|
|
create_table_from_parquet(self.client, unique_database, 'double_nested_decimals')
|
|
create_table_from_parquet(self.client, unique_database, 'alltypes_tiny_pages')
|
|
create_table_from_parquet(self.client, unique_database, 'alltypes_tiny_pages_plain')
|
|
create_table_from_parquet(self.client, unique_database, 'alltypes_empty_pages')
|
|
create_table_from_parquet(self.client, unique_database, 'alltypes_invalid_pages')
|
|
create_table_from_parquet(self.client, unique_database,
|
|
'customer_multiblock_page_index')
|
|
|
|
for batch_size in [0, 1]:
|
|
new_vector.get_value('exec_option')['batch_size'] = batch_size
|
|
self.run_test_case('QueryTest/parquet-page-index', new_vector, unique_database)
|
|
self.run_test_case('QueryTest/nested-types-parquet-page-index', new_vector,
|
|
unique_database)
|
|
self.run_test_case('QueryTest/parquet-page-index-alltypes-tiny-pages', new_vector,
|
|
unique_database)
|
|
self.run_test_case('QueryTest/parquet-page-index-alltypes-tiny-pages-plain',
|
|
new_vector, unique_database)
|
|
|
|
for batch_size in [0, 1, 2, 3, 4, 8, 16, 32, 64, 128, 256, 512]:
|
|
new_vector.get_value('exec_option')['batch_size'] = batch_size
|
|
self.run_test_case('QueryTest/parquet-page-index-large', new_vector,
|
|
unique_database)
|
|
# Test for the bugfix
|
|
self.run_test_case('QueryTest/parquet-page-index-bugfix', vector, unique_database)
|