Quanlong Huang created IMPALA-15290:
---------------------------------------
Summary: test_execute_remove_orphan_files fails in file existence
check
Key: IMPALA-15290
URL: https://issues.apache.org/jira/browse/IMPALA-15290
Project: IMPALA
Issue Type: Bug
Reporter: Quanlong Huang
Stacktrace
{noformat}
query_test/test_iceberg.py:502: in test_execute_remove_orphan_files
assert self.filesystem_client.exists(os.path.join(DATA_PATH, file_parq1))
E AssertionError: assert False
E + where False = <bound method HadoopFsCommandLineClient.exists of
<tests.util.hdfs_util.HadoopFsCommandLineClient object at
0x7fd3a9a06d10>>('/test-warehouse/test_execute_remove_orphan_files_1e8edd5.db/tbl_with_orphan_files/data/00000-0-data-gfurnstahl_20220906113044_157fc172-f5d3-4c70-8653-fff150b6136a-job_16619542960420_0002-1-00001.parquet')
E + where <bound method HadoopFsCommandLineClient.exists of
<tests.util.hdfs_util.HadoopFsCommandLineClient object at 0x7fd3a9a06d10>> =
<tests.util.hdfs_util.HadoopFsCommandLineClient object at 0x7fd3a9a06d10>.exists
E + where <tests.util.hdfs_util.HadoopFsCommandLineClient object at
0x7fd3a9a06d10> = <test_iceberg.TestIcebergTable object at
0x7fd3a98e8950>.filesystem_client
E + and
'/test-warehouse/test_execute_remove_orphan_files_1e8edd5.db/tbl_with_orphan_files/data/00000-0-data-gfurnstahl_20220906113044_157fc172-f5d3-4c70-8653-fff150b6136a-job_16619542960420_0002-1-00001.parquet'
= <function join at
0x7fd3b6e34f40>('/test-warehouse/test_execute_remove_orphan_files_1e8edd5.db/tbl_with_orphan_files/data',
'00000-0-data-gfurnstahl_20220906113044_157fc172-f5d3-4c70-8653-fff150b6136a-job_16619542960420_0002-1-00001.parquet')
E + where <function join at 0x7fd3b6e34f40> = <module 'posixpath'
(frozen)>.join
E + where <module 'posixpath' (frozen)> = os.path
DATA_PATH =
'/test-warehouse/test_execute_remove_orphan_files_1e8edd5.db/tbl_with_orphan_files/data'
METADATA_PATH =
'/test-warehouse/test_execute_remove_orphan_files_1e8edd5.db/tbl_with_orphan_files/metadata'
SRC_DIR =
'/data/jenkins/workspace/impala-asf-master-core-s3-data-cache/repos/Impala/testdata/data/iceberg_test/iceberg_mixed_file_format_test/{0}/{1}'
TABLE_PATH =
'/test-warehouse/test_execute_remove_orphan_files_1e8edd5.db/tbl_with_orphan_files'
db_tbl =
'test_execute_remove_orphan_files_1e8edd5.tbl_with_orphan_files'
file_avro1 = '055baf62-de6d-4583-bf21-f187f9482343-m0.avro'
file_parq1 =
'00000-0-data-gfurnstahl_20220906113044_157fc172-f5d3-4c70-8653-fff150b6136a-job_16619542960420_0002-1-00001.parquet'
impalad_client = <tests.common.impala_connection.ImpylaHS2Connection
object at 0x7fd3a9aa06d0>
insert_q = 'insert into {0} values ({1})'
result = <tests.common.impala_connection.ImpylaHS2ResultSet object
at 0x7fd3a9aa3590>
self = <test_iceberg.TestIcebergTable object at 0x7fd3a98e8950>
tbl_name = 'tbl_with_orphan_files'
unique_database = 'test_execute_remove_orphan_files_1e8edd5'{noformat}
The code is:
{code:python}
494 # Copy first set of junk files.
495 file_parq1 =
"00000-0-data-gfurnstahl_20220906113044_157fc172-f5d3-4c70-8653-" \
496 "fff150b6136a-job_16619542960420_0002-1-00001.parquet"
497 file_avro1 = "055baf62-de6d-4583-bf21-f187f9482343-m0.avro"
498 self.filesystem_client.copy_from_local(
499 SRC_DIR.format('data', file_parq1), DATA_PATH)
500 self.filesystem_client.copy_from_local(
501 SRC_DIR.format('metadata', file_avro1), METADATA_PATH)
502 assert self.filesystem_client.exists(os.path.join(DATA_PATH,
file_parq1))
503 assert self.filesystem_client.exists(os.path.join(METADATA_PATH,
file_avro1)){code}
https://github.com/apache/impala/blob/2157bc8278dd9db8dcb7dc77d982919a9d61f4b0/tests/query_test/test_iceberg.py#L502
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
