[
https://issues.apache.org/jira/browse/IMPALA-15514?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Arnab Karmakar resolved IMPALA-15514.
-------------------------------------
Resolution: Fixed
> TestIcebergTable.test_iceberg_uuid_type failing on S3 builds
> ------------------------------------------------------------
>
> Key: IMPALA-15514
> URL: https://issues.apache.org/jira/browse/IMPALA-15514
> Project: IMPALA
> Issue Type: Bug
> Reporter: Arnab Karmakar
> Assignee: Arnab Karmakar
> Priority: Major
>
> TestIcebergTable.test_iceberg_uuid_type failing on S3 builds:
> Error message:
> {code:java}
> AssertionError: Could not find expected row row_regex: .*HDFS partitions=4/4
> files=4 .* in actual rows:
> ' Iceberg snapshot id: 2882928824223409296'
> ' S3 partitions=4/4 files=4 size=4.00KB'
> ' predicates: uuid_bucket = '12345678-1234-5678-1234-567812345678''
> ' row-size=20B cardinality=1'
> ''
> '00:SCAN S3 [test_iceberg_uuid_type_93b7813.iceberg_uuid_test_part]'
> '01:EXCHANGE [UNPARTITIONED]'
> 'Max Per-Host Resource Reservation: Memory=4.02MB Threads=3'
> 'PLAN-ROOT SINK'
> 'Per-Host Resource Estimates: Memory=36MB'
> 'WARNING: The following tables are missing relevant table and/or column
> statistics.'
> 'test_iceberg_uuid_type_93b7813.iceberg_uuid_test_part'
> '|'
> '|'
> assert False{code}
> Stack Trace:
> {code:java}
> query_test/test_iceberg.py:97: in test_iceberg_uuid_type
> self.run_test_case('QueryTest/iceberg-uuid-type', vector,
> use_db=unique_database)
> self = <test_iceberg.TestIcebergTable object at 0xffff9f707710>
> unique_database = 'test_iceberg_uuid_type_93b7813'
> uuid_fixture_dir =
> '${IMPALA_HOME}/testdata/data/iceberg_test/iceberg_uuid'
> 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}"
> common/impala_test_suite.py:1086: in run_test_case
> self.__verify_results_and_errors(vector, test_section,
> results_section_name,
> _ImpalaTestSuite__exec_in_hive = <function
> ImpalaTestSuite.run_test_case.<locals>.__exec_in_hive at 0xffff9f8172e0>
> _ImpalaTestSuite__exec_in_impala = <function
> ImpalaTestSuite.run_test_case.<locals>.__exec_in_impala at 0xffff9f817ce0>
> _ImpalaTestSuite__exec_in_trino = <function
> ImpalaTestSuite.run_test_case.<locals>.__exec_in_trino at 0xffff9f817ec0>
> catch_section_name = 'CATCH'
> current_error = None
> encoding = None
> exec_fn = <function
> ImpalaTestSuite.run_test_case.<locals>.__exec_in_impala at 0xffff9f817ce0>
> 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 0xffff9f6ac9d0>
> lineage_log_dir = ''
> multiple_impalad = False
> protocol = 'hs2'
> query = "EXPLAIN SELECT id FROM iceberg_uuid_test_part\nWHERE
> uuid_bucket = CAST('12345678-1234-5678-1234-567812345678' AS UUID)"
> query_section = "# UUID value predicates stay in the scan and Iceberg
> prunes no data files.\nEXPLAIN SELECT id FROM iceberg_uuid_test_part\nWHERE
> uuid_bucket = CAST('12345678-1234-5678-1234-567812345678' AS UUID);\n"
> result = <tests.common.impala_connection.ImpylaHS2ResultSet
> object at 0xffff9f7bcc10>
> result_list = []
> results_section_name = 'RESULTS'
> rt_profile_info = None
> sections = [defaultdict(<class 'str'>, {'QUERY': '# Iceberg UUID
> Parquet read-path tests.\nDESCRIBE iceberg_uuid_test\n', 'VERIFI... AS
> ICEBERG\nAS SELECT * FROM iceberg_uuid_test\n', 'CATCH': ['Impala does not
> support writing UUID columns\n']}), ...]
> self = <test_iceberg.TestIcebergTable object at 0xffff9f707710>
> table_format_info = <tests.common.test_dimensions.TableFormatInfo
> object at 0xffffa180c290>
> target_impalad_clients =
> [<tests.common.impala_connection.ImpylaHS2Connection object at
> 0xffff9f6ac9d0>]
> test_file_name = 'QueryTest/iceberg-uuid-type'
> test_file_vars = None
> test_section = defaultdict(<class 'str'>, {'QUERY': "# UUID value
> predicates stay in the scan and Iceberg prunes no data files.\nEXPL...es=4
> .*\nrow_regex: .* predicates: uuid_bucket =
> ''12345678-1234-5678-1234-567812345678''.*\n", 'TYPES': 'STRING\n'})
> total_count = 91
> use_db = 'test_iceberg_uuid_type_93b7813'
> user = None
> 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}"
> common/impala_test_suite.py:852: 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 0xffff9f7bcc10>
> result_section = 'RESULTS'
> result_section_name = 'RESULTS'
> section_name = 'ERRORS'
> self = <test_iceberg.TestIcebergTable object at 0xffff9f707710>
> test_section = defaultdict(<class 'str'>, {'QUERY': "# UUID value
> predicates stay in the scan and Iceberg prunes no data files.\nEXPL...es=4
> .*\nrow_regex: .* predicates: uuid_bucket =
> ''12345678-1234-5678-1234-567812345678''.*\n", 'TYPES': 'STRING\n'})
> type_section = 'TYPES'
> use_db = 'test_iceberg_uuid_type_93b7813'
> 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}"
> common/test_result_verifier.py:505: in verify_raw_results
> VERIFIER_MAP[verifier](expected, actual)
> actual = <tests.common.test_result_verifier.QueryTestResult
> object at 0xffff9f6c4e50>
> actual_labels = ['EXPLAIN STRING']
> actual_types = ['STRING']
> exec_result = <tests.common.impala_connection.ImpylaHS2ResultSet
> object at 0xffff9f7bcc10>
> expected = <tests.common.test_result_verifier.QueryTestResult
> object at 0xffffa1c40690>
> expected_results = "row_regex: .*HDFS partitions=4/4 files=4
> .*\nrow_regex: .* predicates: uuid_bucket =
> ''12345678-1234-5678-1234-567812345678''.*\n"
> expected_results_list = ['row_regex: .*HDFS partitions=4/4 files=4
> .*', "row_regex: .* predicates: uuid_bucket =
> ''12345678-1234-5678-1234-567812345678''.*"]
> expected_types = ['STRING']
> file_format = 'parquet'
> is_raw_string = False
> order_matters = False
> protocol = 'hs2'
> replace_filenames = True
> result_section = 'RESULTS'
> section = 'STRING\n'
> test_section = defaultdict(<class 'str'>, {'QUERY': "# UUID value
> predicates stay in the scan and Iceberg prunes no data files.\nEXPL...es=4
> .*\nrow_regex: .* predicates: uuid_bucket =
> ''12345678-1234-5678-1234-567812345678''.*\n", 'TYPES': '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'
> common/test_result_verifier.py:272: 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: .*HDFS
> partitions=4/4 files=4 .* in actual rows:
> E ' Iceberg snapshot id: 2882928824223409296'
> E ' S3 partitions=4/4 files=4 size=4.00KB'
> E ' predicates: uuid_bucket = '12345678-1234-5678-1234-567812345678''
> E ' row-size=20B cardinality=1'
> E ''
> E '00:SCAN S3 [test_iceberg_uuid_type_93b7813.iceberg_uuid_test_part]'
> E '01:EXCHANGE [UNPARTITIONED]'
> E 'Max Per-Host Resource Reservation: Memory=4.02MB Threads=3'
> E 'PLAN-ROOT SINK'
> E 'Per-Host Resource Estimates: Memory=36MB'
> E 'WARNING: The following tables are missing relevant table and/or column
> statistics.'
> E 'test_iceberg_uuid_type_93b7813.iceberg_uuid_test_part'
> E '|'
> E '|'
> E assert False
> actual_literal_strings = {"' Iceberg snapshot id:
> 2882928824223409296'", "' S3 partitions=4/4 files=4 size=4.00KB'", "'
> predicates: uuid_..., "' row-size=20B cardinality=1'", "''", "'00:SCAN S3
> [test_iceberg_uuid_type_93b7813.iceberg_uuid_test_part]'", ...}
> actual_results = <tests.common.test_result_verifier.QueryTestResult
> object at 0xffff9f6c4e50>
> actual_row = <tests.common.test_result_verifier.ResultRow object at
> 0xffff9f6c7810>
> expected_literal_strings = set()
> expected_literals = []
> expected_non_literals = [<tests.common.test_result_verifier.ResultRow
> object at 0xffff9fa93950>, <tests.common.test_result_verifier.ResultRow
> object at 0xffff9f7bf150>]
> expected_results = <tests.common.test_result_verifier.QueryTestResult
> object at 0xffffa1c40690>
> expected_row = <tests.common.test_result_verifier.ResultRow object at
> 0xffff9f7bf150>
> matched = False{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
