anoopj commented on PR #3015:
URL: https://github.com/apache/iceberg-rust/pull/3015#issuecomment-5322136119

   >  Re-running the benchmark through the actual function would give a more 
representative number.
   
   Good point. I  re-ran the measurement by streaming the batches through 
`parse_positional_deletes_record_batch_stream` itself on release build, 500k 
rows in 8192-row batches with S3-style paths sorted by (file_path, pos). 
   
   Result shows a 4x improvement. The per-row file_path.to_string() + hash + 
entry lookup was dominating, so the shared per-row overhead didn't dilute the 
ratio that much.  I have updated the description


-- 
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]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to