Quanlong Huang created IMPALA-15291:
---------------------------------------
Summary: TestDisabledBlockLocations.test_iceberg_smoke fails in
erasure-coding builds
Key: IMPALA-15291
URL: https://issues.apache.org/jira/browse/IMPALA-15291
Project: IMPALA
Issue Type: Bug
Reporter: Quanlong Huang
TestDisabledBlockLocations.test_iceberg_smoke fails in a erasure-coding build
{code:java}
custom_cluster.test_disabled_block_locations.TestDisabledBlockLocations.test_iceberg_smoke["table_format:
text/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}"]{code}
The query is "show files in iceberg_hadoop_cat".
The expected "EC Policy" is $ERASURECODE_POLICY which is 'RS-3-2-1024k'. But
the actual output is 'NONE'.
Error message
{noformat}
AssertionError: assert Comparing QueryTestResults (expected vs actual):
row_regex:'hdfs://localhost:20500/test-warehouse/test_iceberg_smoke_cfe9c6f2.db/hadoop_catalog_test/test_iceberg_smoke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'
!=
'hdfs://localhost:20500/test-warehouse/test_iceberg_smoke_cfe9c6f2.db/hadoop_catalog_test/test_iceberg_smoke_cfe9c6f2/iceberg_hadoop_cat/data/aa425499819415c2-7ffb9dfc00000000_1352165222_data.0.parq','360B','','NONE'{noformat}
Stacktrace
{noformat}
custom_cluster/test_disabled_block_locations.py:53: in test_iceberg_smoke
self.run_test_case('QueryTest/iceberg-insert', vector, unique_database)
self =
<tests.custom_cluster.test_disabled_block_locations.TestDisabledBlockLocations
object at 0x7f3a151beb10>
unique_database = 'test_iceberg_smoke_cfe9c6f2'
vector = "table_format: text/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 0x7f3a14feede0>
_ImpalaTestSuite__exec_in_impala = <function
ImpalaTestSuite.run_test_case.<locals>.__exec_in_impala at 0x7f3a14fefce0>
_ImpalaTestSuite__exec_in_trino = <function
ImpalaTestSuite.run_test_case.<locals>.__exec_in_trino at 0x7f3a14fef2e0>
catch_section_name = 'CATCH'
current_error = None
encoding = None
exec_fn = <function
ImpalaTestSuite.run_test_case.<locals>.__exec_in_impala at 0x7f3a14fefce0>
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 0x7f3a151bdf50>
lineage_log_dir = ''
multiple_impalad = False
protocol = 'hs2'
query = 'show files in iceberg_hadoop_cat'
query_section = 'show files in iceberg_hadoop_cat;\n'
result = <tests.common.impala_connection.ImpylaHS2ResultSet object
at 0x7f3ab80c0d10>
result_list = []
results_section_name = 'RESULTS'
rt_profile = []
rt_profile_info = None
sections = [defaultdict(<class 'str'>, {'QUERY': "# Create a table
that is a subset of 'alltypes' table, i.e. it only\n# contains...': '# Create
non-Iceberg table with INT96 nanos.\ncreate table int96_nanos (ts timestamp)
stored as parquet;\n'}), ...]
self =
<tests.custom_cluster.test_disabled_block_locations.TestDisabledBlockLocations
object at 0x7f3a151beb10>
table_format_info = <tests.common.test_dimensions.TableFormatInfo
object at 0x7f3ab8d87ad0>
target_impalad_clients =
[<tests.common.impala_connection.ImpylaHS2Connection object at 0x7f3a151bdf50>]
test_file_name = 'QueryTest/iceberg-insert'
test_file_vars = None
test_section = defaultdict(<class 'str'>, {'QUERY': 'show files in
iceberg_hadoop_cat;\n', 'RESULTS':
"row_regex:'hdfs://localhost:20...ke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'\n",
'TYPES': 'STRING, STRING, STRING, STRING\n'})
total_count = 11
use_db = 'test_iceberg_smoke_cfe9c6f2'
user = None
vector = "table_format: text/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 0x7f3ab80c0d10>
result_section = 'RESULTS'
result_section_name = 'RESULTS'
section_name = 'ERRORS'
self =
<tests.custom_cluster.test_disabled_block_locations.TestDisabledBlockLocations
object at 0x7f3a151beb10>
test_section = defaultdict(<class 'str'>, {'QUERY': 'show files in
iceberg_hadoop_cat;\n', 'RESULTS':
"row_regex:'hdfs://localhost:20...ke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'\n",
'TYPES': 'STRING, STRING, STRING, STRING\n'})
type_section = 'TYPES'
use_db = 'test_iceberg_smoke_cfe9c6f2'
vector = "table_format: text/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 0x7f3a1107ca10>
actual_labels = ['PATH', 'SIZE', 'PARTITION', 'EC POLICY']
actual_types = ['STRING', 'STRING', 'STRING', 'STRING']
exec_result = <tests.common.impala_connection.ImpylaHS2ResultSet object
at 0x7f3ab80c0d10>
expected = <tests.common.test_result_verifier.QueryTestResult object
at 0x7f3ab90eecd0>
expected_results =
"row_regex:'hdfs://localhost:20500/test-warehouse/test_iceberg_smoke_cfe9c6f2.db/hadoop_catalog_test/test_iceberg_smoke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'\n"
expected_results_list =
["row_regex:'hdfs://localhost:20500/test-warehouse/test_iceberg_smoke_cfe9c6f2.db/hadoop_catalog_test/test_iceberg_smoke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'"]
expected_types = ['STRING', 'STRING', 'STRING', 'STRING']
file_format = 'text'
is_raw_string = False
order_matters = False
protocol = 'hs2'
replace_filenames = True
result_section = 'RESULTS'
section = 'STRING, STRING, STRING, STRING\n'
test_section = defaultdict(<class 'str'>, {'QUERY': 'show files in
iceberg_hadoop_cat;\n', 'RESULTS':
"row_regex:'hdfs://localhost:20...ke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'\n",
'TYPES': 'STRING, STRING, STRING, STRING\n'})
type_section = 'TYPES'
update_section = False
vector = "table_format: text/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 = None
common/test_result_verifier.py:296: in verify_query_result_is_equal
assert expected_results == actual_results
E AssertionError: assert Comparing QueryTestResults (expected vs actual):
E
row_regex:'hdfs://localhost:20500/test-warehouse/test_iceberg_smoke_cfe9c6f2.db/hadoop_catalog_test/test_iceberg_smoke_cfe9c6f2/iceberg_hadoop_cat/data/.*.0.parq','.*','','RS-3-2-1024k'
!=
'hdfs://localhost:20500/test-warehouse/test_iceberg_smoke_cfe9c6f2.db/hadoop_catalog_test/test_iceberg_smoke_cfe9c6f2/iceberg_hadoop_cat/data/aa425499819415c2-7ffb9dfc00000000_1352165222_data.0.parq','360B','','NONE'
actual_results = <tests.common.test_result_verifier.QueryTestResult
object at 0x7f3a1107ca10>
expected_results = <tests.common.test_result_verifier.QueryTestResult
object at 0x7f3ab90eecd0>{noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
