We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
If we have a skewed join that has GPU written output, we may end up with needing to read by range.
Currently the RapidsShuffleManager will "delegate" to the cpu shuffle for this, but this will fail (the output was written the catalog, not to files).
This is to implement getReaderForRange
getReaderForRange
Note that in spark 3.1, getReader became final, and we should only use getReaderForRange.
getReader
The text was updated successfully, but these errors were encountered:
Closing in favor of issue #455
Sorry, something went wrong.
Add new native parquet footer API and deprecate the old one (NVIDIA#362)
ba5de10
Signed-off-by: Robert (Bobby) Evans <[email protected]>
No branches or pull requests
If we have a skewed join that has GPU written output, we may end up with needing to read by range.
Currently the RapidsShuffleManager will "delegate" to the cpu shuffle for this, but this will fail (the output was written the catalog, not to files).
This is to implement
getReaderForRange
Note that in spark 3.1,
getReader
became final, and we should only usegetReaderForRange
.The text was updated successfully, but these errors were encountered: