adriangb opened a new pull request, #10021:
URL: https://github.com/apache/arrow-rs/pull/10021

   # Which issue does this PR close?
   
   Split out of #9972 per [this review 
comment](https://github.com/apache/arrow-rs/pull/9972#discussion_r3307256819).
   
   # Rationale for this change
   
   #9972 makes the parquet writer's mini-batch sizing byte-budget aware so 
large variable-width values don't produce oversized data pages. To measure that 
change against a stable baseline — and in particular to see the difference in 
the large-string case — these benchmarks belong on `main` first.
   
   # What changes are included in this PR?
   
   Adds two BYTE_ARRAY write cases to the `arrow_writer` criterion bench:
   
   - **`short_string_non_null`** — 1M fixed-width 8-byte strings. The 
small-value hot path, where byte-budget-based sub-batch sizing should always 
resolve to the full chunk (no granular splitting, no regression).
   - **`large_string_non_null`** — 1024 × 256 KiB strings (256 MiB total). The 
large-value case: with the default 1 MiB page byte limit each value needs its 
own page, and a `write_batch_size` of 1024 would otherwise buffer all 256 MiB 
before the post-write size check runs.
   
   No library code changes — benchmarks only.
   
   # Are there any user-facing changes?
   
   No.
   
   🤖 Generated with [Claude Code](https://claude.com/claude-code)


-- 
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