Dániel Gábor Vankó created IMPALA-14692:
-------------------------------------------
Summary: test_spilling_hash_join is failing without greedy regex
Key: IMPALA-14692
URL: https://issues.apache.org/jira/browse/IMPALA-14692
Project: IMPALA
Issue Type: Bug
Reporter: Dániel Gábor Vankó
Assignee: Dániel Gábor Vankó
query_test/test_join_queries.py::TestSpillingHashJoin::test_spilling_hash_join
is failing since IMPALA-14680, seemingly without no reason, but for other
row_regex lines there is a space between the row_regex: and the pattern, which
is missing here.
This test runs only in exhaustive mode.
h4. Stacktrace:
{noformat}
query_test/test_join_queries.py:247: in test_spilling_hash_join
self.run_test_case('QueryTest/query-impala-13138', vector, unique_database)
i = 0
self = <test_join_queries.TestSpillingHashJoin object at
0x7f36a4cab9a0>
unique_database = 'test_spilling_hash_join_28ff9a90'
vector = "table_format: parquet/none" | "protocol: hs2" |
"exec_option: {'abort_on_error': 1, 'batch_size': 0, 'disable_codegen': False,
'disable_codegen_rows_threshold': 0, 'exec_single_node_rows_threshold': 0,
'num_nodes': 0, 'test_replan': 1}"
/data/jenkins/workspace/impala-cdw-master-exhaustive/repos/Impala/tests/common/impala_test_suite.py:987:
in run_test_case
self.__verify_results_and_errors(vector, test_section, result, use_db)
_ImpalaTestSuite__exec_in_hive = <function
ImpalaTestSuite.run_test_case.<locals>.__exec_in_hive at 0x7f36a511a0d0>
_ImpalaTestSuite__exec_in_impala = <function
ImpalaTestSuite.run_test_case.<locals>.__exec_in_impala at 0x7f36a511a3a0>
current_error = None
encoding = None
exec_fn = <function
ImpalaTestSuite.run_test_case.<locals>.__exec_in_impala at 0x7f36a511a3a0>
exec_options = {'abort_on_error': 1, 'batch_size': 0,
'disable_codegen': False, 'disable_codegen_rows_threshold': 0, ...}
failed_count = 0
impalad_client = <tests.common.impala_connection.ImpylaHS2Connection
object at 0x7f36a4cab250>
impalad_clients = [<tests.common.impala_connection.ImpylaHS2Connection
object at 0x7f36a4cab250>]
lineage_log_dir = ''
multiple_impalad = False
protocol = 'hs2'
query = "set RUNTIME_FILTER_WAIT_TIME_MS=10000;\nset
MT_DOP=12;\nset RUNTIME_FILTER_MIN_SIZE=8192;\nset
RUNTIME_FILTER_MAX_SIZ...>='2024-06-01'\n AND re.send_account_sk not in
(43)\n GROUP BY ecc.letter_mission_name, re.`date`, c.war_group"
query_section = "set RUNTIME_FILTER_WAIT_TIME_MS=10000;\nset
MT_DOP=12;\nset RUNTIME_FILTER_MIN_SIZE=8192;\nset
RUNTIME_FILTER_MAX_SIZ...2024-06-01'\n AND re.send_account_sk not in
(43)\n GROUP BY ecc.letter_mission_name, re.`date`, c.war_group;\n"
result = <tests.common.impala_connection.ImpylaHS2ResultSet object
at 0x7f36a4db4fd0>
result_list = []
sections = [defaultdict(<class 'str'>, {'QUERY': "set
RUNTIME_FILTER_WAIT_TIME_MS=10000;\nset MT_DOP=12;\nset
RUNTIME_FILTER_MIN_...roup;\n", 'VERIFIER': 'VERIFY_IS_SUBSET', 'RESULTS':
"row_regex:,'2024-06-07',\n", 'TYPES': 'STRING,STRING,STRING\n'})]
self = <test_join_queries.TestSpillingHashJoin object at
0x7f36a4cab9a0>
table_format_info = <tests.common.test_dimensions.TableFormatInfo
object at 0x7f36a922f460>
target_feng_real_impalad_clients = []
target_impalad_clients =
[<tests.common.impala_connection.ImpylaHS2Connection object at 0x7f36a4cab250>]
test_file_name = 'QueryTest/query-impala-13138'
test_file_vars = None
test_section = defaultdict(<class 'str'>, {'QUERY': "set
RUNTIME_FILTER_WAIT_TIME_MS=10000;\nset MT_DOP=12;\nset
RUNTIME_FILTER_MIN_S...group;\n", 'VERIFIER': 'VERIFY_IS_SUBSET', 'RESULTS':
"row_regex:,'2024-06-07',\n", 'TYPES': 'STRING,STRING,STRING\n'})
total_count = 1
use_db = 'test_spilling_hash_join_28ff9a90'
vector = "table_format: parquet/none" | "protocol: hs2" |
"exec_option: {'abort_on_error': 1, 'batch_size': 0, 'disable_codegen': False,
'disable_codegen_rows_threshold': 0, 'exec_single_node_rows_threshold': 0,
'num_nodes': 0, 'test_replan': 1}"
/data/jenkins/workspace/impala-cdw-master-exhaustive/repos/Impala/tests/common/impala_test_suite.py:782:
in __verify_results_and_errors
verify_raw_results(test_section, result, vector,
replace_filenames_with_placeholder = True
result = <tests.common.impala_connection.ImpylaHS2ResultSet object
at 0x7f36a4db4fd0>
result_section = 'RESULTS'
section_name = 'ERRORS'
self = <test_join_queries.TestSpillingHashJoin object at
0x7f36a4cab9a0>
test_section = defaultdict(<class 'str'>, {'QUERY': "set
RUNTIME_FILTER_WAIT_TIME_MS=10000;\nset MT_DOP=12;\nset
RUNTIME_FILTER_MIN_S...group;\n", 'VERIFIER': 'VERIFY_IS_SUBSET', 'RESULTS':
"row_regex:,'2024-06-07',\n", 'TYPES': 'STRING,STRING,STRING\n'})
type_section = 'TYPES'
use_db = 'test_spilling_hash_join_28ff9a90'
vector = "table_format: parquet/none" | "protocol: hs2" |
"exec_option: {'abort_on_error': 1, 'batch_size': 0, 'disable_codegen': False,
'disable_codegen_rows_threshold': 0, 'exec_single_node_rows_threshold': 0,
'num_nodes': 0, 'test_replan': 1}"
/data/jenkins/workspace/impala-cdw-master-exhaustive/repos/Impala/tests/common/test_result_verifier.py:540:
in verify_raw_results
VERIFIER_MAP[verifier](expected, actual)
actual = <tests.common.test_result_verifier.QueryTestResult object
at 0x7f36a4db4be0>
actual_labels = ['LETTER_MISSION_NAME', 'DATE_', 'WAR_GROUP']
actual_types = ['STRING', 'STRING', 'STRING']
exec_result = <tests.common.impala_connection.ImpylaHS2ResultSet object
at 0x7f36a4db4fd0>
expected = <tests.common.test_result_verifier.QueryTestResult object
at 0x7f36a4db4b20>
expected_results = "row_regex:,'2024-06-07',\n"
expected_results_list = ["row_regex:,'2024-06-07',"]
expected_types = ['STRING', 'STRING', 'STRING']
file_format = 'parquet'
is_raw_string = False
order_matters = True
protocol = 'hs2'
replace_filenames = True
result_section = 'RESULTS'
section = 'STRING,STRING,STRING\n'
test_section = defaultdict(<class 'str'>, {'QUERY': "set
RUNTIME_FILTER_WAIT_TIME_MS=10000;\nset MT_DOP=12;\nset
RUNTIME_FILTER_MIN_S...group;\n", 'VERIFIER': 'VERIFY_IS_SUBSET', 'RESULTS':
"row_regex:,'2024-06-07',\n", 'TYPES': 'STRING,STRING,STRING\n'})
type_section = 'TYPES'
update_section = False
vector = "table_format: parquet/none" | "protocol: hs2" |
"exec_option: {'abort_on_error': 1, 'batch_size': 0, 'disable_codegen': False,
'disable_codegen_rows_threshold': 0, 'exec_single_node_rows_threshold': 0,
'num_nodes': 0, 'test_replan': 1}"
verifier = 'VERIFY_IS_SUBSET'
/data/jenkins/workspace/impala-cdw-master-exhaustive/repos/Impala/tests/common/test_result_verifier.py:298:
in verify_query_result_is_subset
assert matched, u"Could not find expected row {0} in actual
rows:\n{1}".format(
E AssertionError: Could not find expected row row_regex:,'2024-06-07', in
actual rows:
E 'NULL','2024-06-07','47'
E 'NULL','2024-06-07','42'
E 'NULL','2024-06-07','11'
E 'name','2024-06-07','20'
E 'NULL','2024-06-07','7'
E 'name','2024-06-07','5'
E 'NULL','2024-06-07','20'
E 'NULL','2024-06-07','NULL'
E 'name','2024-06-07','31'
E 'NULL','2024-06-07','25'
E 'name','2024-06-07','48'
E 'name','2024-06-07','34'
E 'NULL','2024-06-07','2'
E 'NULL','2024-06-07','8'
E 'name','2024-06-07','25'
E 'NULL','2024-06-07','48'
E 'name','2024-06-07','16'
E 'name','2024-06-07','45'
E 'NULL','2024-06-07','14'
E 'NULL','2024-06-07','34'
E 'name','2024-06-07','2'
E 'name','2024-06-07','7'
E 'NULL','2024-06-07','war_group'
E 'name','2024-06-07','42'
E 'name','2024-06-07','11'
E 'name','2024-06-07','14'
E 'name','2024-06-07','0'
E 'name','2024-06-07','47'
E 'NULL','2024-06-07','39'
E 'NULL','2024-06-07','19'
E 'name','2024-06-07','39'
E 'NULL','2024-06-07','31'
E 'NULL','2024-06-07','33'
E 'NULL','2024-06-07','22'
E 'NULL','2024-06-07','10'
E 'NULL','2024-06-07','13'
E 'name','2024-06-07','36'
E 'NULL','2024-06-07','45'
E 'NULL','2024-06-07','27'
E 'name','2024-06-07','13'
E 'name','2024-06-07','28'
E 'name','2024-06-07','40'
E 'NULL','2024-06-07','40'
E 'name','2024-06-07','19'
E 'NULL','2024-06-07','3'
E 'NULL','2024-06-07','6'
E 'NULL','2024-06-07','43'
E 'NULL','2024-06-07','36'
E 'name','2024-06-07','35'
E 'NULL','2024-06-07','0'
E 'NULL','2024-06-07','16'
E 'name','2024-06-07','8'
E 'name','2024-06-07','33'
E 'NULL','2024-06-07','32'
E 'name','2024-06-07','24'
E 'NULL','2024-06-07','46'
E 'NULL','2024-06-07','15'
E 'name','2024-06-07','43'
E 'name','2024-06-07','27'
E 'NULL','2024-06-07','21'
E 'NULL','2024-06-07','35'
E 'NULL','2024-06-07','49'
E 'name','2024-06-07','10'
E 'name','2024-06-07','21'
E 'name','2024-06-07','9'
E 'name','2024-06-07','26'
E 'NULL','2024-06-07','44'
E 'NULL','2024-06-07','26'
E 'name','2024-06-07','3'
E 'NULL','2024-06-07','30'
E 'NULL','2024-06-07','37'
E 'name','2024-06-07','6'
E 'NULL','2024-06-07','5'
E 'NULL','2024-06-07','28'
E 'name','2024-06-07','22'
E 'name','2024-06-07','30'
E 'name','2024-06-07','41'
E 'name','2024-06-07','29'
E 'name','2024-06-07','38'
E 'name','2024-06-07','17'
E 'NULL','2024-06-07','1'
E 'name','2024-06-07','49'
E 'NULL','2024-06-07','24'
E 'name','2024-06-07','15'
E 'name','2024-06-07','1'
E 'name','2024-06-07','war_group'
E 'name','2024-06-07','32'
E 'name','2024-06-07','12'
E 'name','2024-06-07','37'
E 'NULL','2024-06-07','12'
E 'name','2024-06-07','4'
E 'name','2024-06-07','23'
E 'NULL','2024-06-07','29'
E 'NULL','2024-06-07','18'
E 'NULL','2024-06-07','17'
E 'name','2024-06-07','46'
E 'NULL','2024-06-07','9'
E 'NULL','2024-06-07','50'
E 'NULL','2024-06-07','38'
E 'name','2024-06-07','50'
E 'name','2024-06-07','44'
E 'NULL','2024-06-07','41'
E 'name','2024-06-07','18'
E 'NULL','2024-06-07','4'
E 'NULL','2024-06-07','23'
actual_literal_strings = {"'NULL','2024-06-07','0'",
"'NULL','2024-06-07','1'", "'NULL','2024-06-07','10'",
"'NULL','2024-06-07','11'", "'NULL','2024-06-07','12'",
"'NULL','2024-06-07','13'", ...}
actual_results = <tests.common.test_result_verifier.QueryTestResult
object at 0x7f36a4db4be0>
actual_row = <tests.common.test_result_verifier.ResultRow object at
0x7f36a4cb4070>
expected_literal_strings = set()
expected_literals = []
expected_non_literals = [<tests.common.test_result_verifier.ResultRow
object at 0x7f36a4db4b80>]
expected_results = <tests.common.test_result_verifier.QueryTestResult
object at 0x7f36a4db4b20>
expected_row = <tests.common.test_result_verifier.ResultRow object at
0x7f36a4db4b80>
matched = False{noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
