manuzhang commented on PR #11033: URL: https://github.com/apache/iceberg/pull/11033#issuecomment-2345674565
It looks the new UT is flaky https://github.com/apache/iceberg/actions/runs/10825717894/job/30035219384 ``` TestFlinkIcebergSinkRangeDistributionBucketing > testBucketNumberLessThanWriterParallelismNotDivisible() FAILED java.lang.AssertionError: Expecting size of: [GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=0/00003-0-39af39f3-5278-4295-99a1-9720958db8c9-00009.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=0}, record_count=12, file_size_in_bytes=1243, column_sizes=org.apache.iceberg.util.SerializableMap@1a2, value_counts=org.apache.iceberg.util.SerializableMap@2a, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@f366a4f, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@bf4ec4e7, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=1/00003-0-39af39f3-5278-4295-99a1-9720958db8c9-00010.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=1}, record_count=8, file_size_in_bytes=1161, column_sizes=org.apache.iceberg.util.SerializableMap@14c, value_counts=org.apache.iceberg.util.SerializableMap@1e, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@3c0e271f, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@6dbe6441, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=3/00003-0-39af39f3-5278-4295-99a1-9720958db8c9-00008.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=3}, record_count=20, file_size_in_bytes=1399, column_sizes=org.apache.iceberg.util.SerializableMap@23e, value_counts=org.apache.iceberg.util.SerializableMap@42, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@586925d, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@2b469148, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=0/00002-0-73600ead-4c85-4fae-b82b-8ab7eac90cb5-00006.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=0}, record_count=13, file_size_in_bytes=1265, column_sizes=org.apache.iceberg.util.SerializableMap@1b4, value_counts=org.apache.iceberg.util.SerializableMap@29, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@d31dc682, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@8745843, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=1/00002-0-73600ead-4c85-4fae-b82b-8ab7eac90cb5-00007.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=1}, record_count=7, file_size_in_bytes=1140, column_sizes=org.apache.iceberg.util.SerializableMap@139, value_counts=org.apache.iceberg.util.SerializableMap@f, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@b8e44b2e, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@f441240a, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=2/00002-0-73600ead-4c85-4fae-b82b-8ab7eac90cb5-00008.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=2}, record_count=14, file_size_in_bytes=1282, column_sizes=org.apache.iceberg.util.SerializableMap@1c3, value_counts=org.apache.iceberg.util.SerializableMap@28, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@4c23e153, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@38ed4c3b, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=0/00001-0-851323b3-f50a-4bdb-b87e-f3b7563fea20-00007.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=0}, record_count=11, file_size_in_bytes=1221, column_sizes=org.apache.iceberg.util.SerializableMap@188, value_counts=org.apache.iceberg.util.SerializableMap@1b, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@b7fe886e, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@787336c7, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=1/00001-0-851323b3-f50a-4bdb-b87e-f3b7563fea20-00009.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=1}, record_count=10, file_size_in_bytes=1204, column_sizes=org.apache.iceberg.util.SerializableMap@179, value_counts=org.apache.iceberg.util.SerializableMap@1c, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@36958f8c, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@e2d3ea2, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=2/00001-0-851323b3-f50a-4bdb-b87e-f3b7563fea20-00008.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=2}, record_count=14, file_size_in_bytes=1278, column_sizes=org.apache.iceberg.util.SerializableMap@1c1, value_counts=org.apache.iceberg.util.SerializableMap@28, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@f13eaf5d, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@fa07314b, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=0/00005-0-284db009-4695-4493-bd63-ead0e48e6c64-00009.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=0}, record_count=9, file_size_in_bytes=1181, column_sizes=org.apache.iceberg.util.SerializableMap@160, value_counts=org.apache.iceberg.util.SerializableMap@1d, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@34a756d8, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@f881d6ff, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=1/00005-0-284db009-4695-4493-bd63-ead0e48e6c64-00007.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=1}, record_count=9, file_size_in_bytes=1183, column_sizes=org.apache.iceberg.util.SerializableMap@166, value_counts=org.apache.iceberg.util.SerializableMap@1d, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@5a27d75d, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@6548a5f5, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=3/00005-0-284db009-4695-4493-bd63-ead0e48e6c64-00008.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=3}, record_count=19, file_size_in_bytes=1379, column_sizes=org.apache.iceberg.util.SerializableMap@22a, value_counts=org.apache.iceberg.util.SerializableMap@33, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@f3b952e4, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@d60de4c2, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=0/00000-0-04a400d9-3c02-4305-99c4-8a9513f08fb2-00010.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=0}, record_count=9, file_size_in_bytes=1183, column_sizes=org.apache.iceberg.util.SerializableMap@166, value_counts=org.apache.iceberg.util.SerializableMap@1d, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@45e54b10, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@e15527a1, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=1/00000-0-04a400d9-3c02-4305-99c4-8a9513f08fb2-00009.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=1}, record_count=8, file_size_in_bytes=1161, column_sizes=org.apache.iceberg.util.SerializableMap@14c, value_counts=org.apache.iceberg.util.SerializableMap@1e, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@d6177a80, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@b6865eb6, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=2/00000-0-04a400d9-3c02-4305-99c4-8a9513f08fb2-00008.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=2}, record_count=25, file_size_in_bytes=1487, column_sizes=org.apache.iceberg.util.SerializableMap@296, value_counts=org.apache.iceberg.util.SerializableMap@4d, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@f1792380, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@eb1d324a, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=0/00004-0-5299d71e-bdf6-421e-b49e-7a16d08c501b-00008.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=0}, record_count=9, file_size_in_bytes=1184, column_sizes=org.apache.iceberg.util.SerializableMap@165, value_counts=org.apache.iceberg.util.SerializableMap@1d, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@b07f7ca8, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@e4eafce, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=1/00004-0-5299d71e-bdf6-421e-b49e-7a16d08c501b-00010.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=1}, record_count=11, file_size_in_bytes=1223, column_sizes=org.apache.iceberg.util.SerializableMap@188, value_counts=org.apache.iceberg.util.SerializableMap@1b, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@f50f7792, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@76c0af9, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}, GenericDataFile{content=data, file_path=file:/tmp/junit5_hadoop_catalog-6564358266702856210/ecb89cf8-f045-4560-bf48-17bac055481d/default/t/data/ts_hour=2024-09-12-07/uuid_bucket=3/00004-0-5299d71e-bdf6-421e-b49e-7a16d08c501b-00009.parquet, file_format=PARQUET, spec_id=0, partition=PartitionData{ts_hour=479479, uuid_bucket=3}, record_count=22, file_size_in_bytes=1438, column_sizes=org.apache.iceberg.util.SerializableMap@265, value_counts=org.apache.iceberg.util.SerializableMap@40, null_value_counts=org.apache.iceberg.util.SerializableMap@6, nan_value_counts=org.apache.iceberg.util.SerializableMap@0, lower_bounds=org.apache.iceberg.SerializableByteBufferMap@e253791e, upper_bounds=org.apache.iceberg.SerializableByteBufferMap@94c3e62d, key_metadata=null, split_offsets=[4], equality_ids=null, sort_order_id=0, data_sequence_number=4, file_sequence_number=4}] to be less than or equal to 10 but was 18 at org.apache.iceberg.flink.sink.TestFlinkIcebergSinkRangeDistributionBucketing.testParallelism(TestFlinkIcebergSinkRangeDistributionBucketing.java:220) at org.apache.iceberg.flink.sink.TestFlinkIcebergSinkRangeDistributionBucketing.testBucketNumberLessThanWriterParallelismNotDivisible(TestFlinkIcebergSinkRangeDistributionBucketing.java:152) ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
