Expose LayoutStrategy::buffered_bytes through the jni boundary

[robert3005]

This is useful to track write progress since flushed bytes are an underestimate

[github-actions]

Polar Signals Profiling Results

Latest Run

Status	Commit	Job	Attempt	Link
🟢 Done	af5a1e5		1	Explore Profiling Data

Previous Runs (2)

Status	Commit	Job	Attempt	Link
🟢 Done	f71d090		1	Explore Profiling Data
🟢 Done	71b18b5		1	Explore Profiling Data

---

Powered by Polar Signals Cloud

[github-actions]

Benchmarks: Vortex queries 📖

Verdict: No clear signal (medium confidence)
Attributed Vortex impact: +7.7%
Engines: DataFusion No clear signal (+11.1%, environment too noisy confidence) · DuckDB No clear signal (+4.4%, low confidence)
Vortex (geomean): 1.087x ➖
Parquet (geomean): 1.048x ➖
Shifts: Parquet (control) +4.8% · Median polish +7.1%

How to read Verdict and Engines

• Verdict: Overall PR-level signal after subtracting baseline drift estimated from Parquet control rows. It can be Likely improvement, Likely regression, or No clear signal.
• Engines: Per-engine attribution. DataFusion is compared against DataFusion/Parquet controls; DuckDB is compared against DuckDB/Parquet controls. This answers whether each engine improved or regressed independently.
• Confidence: Based on directional consistency, share of rows above the noise floor, and control-run noise.

---

datafusion / vortex-file-compressed (1.171x ❌, 0↑ 2↓)

name	PR af5a1e5 (ns)	base 7654891 (ns)	ratio (PR/base)
vortex_q00/datafusion:vortex-file-compressed 🚨	9735078	8574618	1.14
vortex_q01/datafusion:vortex-file-compressed 🚨	6314904	5229639	1.21

datafusion / parquet (1.054x ➖, 0↑ 1↓)

name	PR af5a1e5 (ns)	base 7654891 (ns)	ratio (PR/base)
vortex_q00/datafusion:parquet	21712677	21568209	1.01
vortex_q01/datafusion:parquet 🚨	5331263	4830857	1.10

duckdb / vortex-file-compressed (1.087x ➖, 0↑ 0↓)

name	PR af5a1e5 (ns)	base 7654891 (ns)	ratio (PR/base)
vortex_q00/duckdb:vortex-file-compressed	11666479	10627404	1.10
vortex_q01/duckdb:vortex-file-compressed	7054921	6551542	1.08

duckdb / parquet (1.042x ➖, 0↑ 0↓)

name	PR af5a1e5 (ns)	base 7654891 (ns)	ratio (PR/base)
vortex_q00/duckdb:parquet	24437304	23559866	1.04
vortex_q01/duckdb:parquet	9985572	9545147	1.05

---

No file size changes detected.

[codspeed-hq]

Merging this PR will improve performance by 26.92%

⚡ 1 improved benchmark
✅ 1846 untouched benchmarks
⏩ 46 skipped benchmarks¹

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
⚡	Simulation	decode_varbin[(1000, 4)]	34.3 µs	27 µs	+26.92%

Tip

Curious why this is faster? Comment @codspeedbot explain why this is faster on this PR, or directly use the CodSpeed MCP with your agent.

---

_{Comparing rk/bufferedbytes (af5a1e5) with develop (7654891)}

Footnotes

1. 46 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩