wForget opened a new issue, #10132:
URL: https://github.com/apache/arrow-rs/issues/10132

   ### Is your feature request related to a problem or challenge?
   
   The current Arrow IPC writer uses the default compression level (which is 3 
by default). 
   
   
https://github.com/apache/arrow-rs/blob/c4a831a1c81be3c20dff510d73954fa6712d90d5/arrow-ipc/src/compression.rs#L40
   
   For compute-performance-sensitive workloads, I would prefer setting it to 
level 1 to achieve faster compression throughput, similar to what is done in 
the datafusion-comet shuffle writer.
   
   
https://github.com/apache/datafusion-comet/blob/af134cf533fb497f542e771ac37cf29322d4eacf/docs/source/contributor-guide/native_shuffle.md?plain=1#L250
   
   Therefore, I'd like to make the compression level configurable.
   
   
   
   
   
   ### Describe the solution you'd like
   
   Add a `batch_compression_level` option to `IpcWriteOptions` and pass it to 
the compressor.
   
   ### Describe alternatives you've considered
   
   _No response_
   
   ### Additional context
   
   _No response_


-- 
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: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to