Open
Description
This was discovered as a byproduct of changes to nvcomp temporary memory usage for decompression. The change caused us to produce a slightly different set of chunks, exposing the underlying bug in the chunked reader itself (nvcomp was not doing anything wrong). Spark Rapids customers have experienced this as well, under difficult-to-reproduce conditions, so having a clean repro case here is nice.
To reproduce, build cudf using nvcomp 4.2.0.11 (#18042) and run the tests. Two of the list tests, ParquetChunkedReaderInputLimitConstrainedTest.MixedColumns
and ParquetChunkedReaderInputLimitTest.List
will throw the exception.
Activity