# Which issue does this PR close?

- Depends on #9723
- Contributes to #9722

# Rationale for this change

`WriterProperties::offset_index_disabled()` checked whether any column
in the `column_properties` HashMap has page-level statistics enabled,
scanning the entire map on every call. This method is called from
`GenericColumnWriter::new` — once per column per row group. With N
columns each having per-column properties, this resulted in quadratic
HashMap iterations during row group construction.

# What changes are included in this PR?

Move the scan into `WriterPropertiesBuilder::build()` so it runs once at
construction time.

Benchmark results (vs baseline in #9723):

```
  writer_overhead/1000_cols/per_column_props     2.44 ms  (was   3.25 ms, −25%)
  writer_overhead/5000_cols/per_column_props    13.28 ms  (was  47.45 ms, −72%)
  writer_overhead/10000_cols/per_column_props   27.97 ms  (was 197.97 ms, −86%)
```

Scaling now linear.

# Are these changes tested?

All tests passing.

# Are there any user-facing changes?

None.

Signed-off-by: Hippolyte Barraud <hippolyte.barraud@datadoghq.com>
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>

# Which issue does this PR close?

- Contributes to apache#9722

# Rationale for this change

Existing writer benchmarks use narrow schemas (5–10 columns) and
primarily measure data encoding throughput. They don't capture
per-column structural overhead that dominates at high column cardinality
(thousands to hundreds of thousands of columns), such as allocation, and
metadata assembly.

# What changes are included in this PR?

This commit adds benchmarks to fill that gap by writing a single-row
batch through `ArrowWriter` with 1k/5k/10k flat `Float32` columns and
per-column `WriterProperties` entries, isolating the cost of the writer
infrastructure itself.

Baseline results (Apple M1 Max):

```
  writer_overhead/1000_cols/per_column_props      3.72 ms
  writer_overhead/5000_cols/per_column_props     54.96 ms
  writer_overhead/10000_cols/per_column_props   220.73 ms
```

# Are these changes tested?

N/A

# Are there any user-facing changes?

N/A

Signed-off-by: Hippolyte Barraud <hippolyte.barraud@datadoghq.com>

…he#9724)

# Which issue does this PR close?

- Depends on apache#9723
- Contributes to apache#9722

# Rationale for this change

`WriterProperties::offset_index_disabled()` checked whether any column
in the `column_properties` HashMap has page-level statistics enabled,
scanning the entire map on every call. This method is called from
`GenericColumnWriter::new` — once per column per row group. With N
columns each having per-column properties, this resulted in quadratic
HashMap iterations during row group construction.

# What changes are included in this PR?

Move the scan into `WriterPropertiesBuilder::build()` so it runs once at
construction time.

Benchmark results (vs baseline in apache#9723):

```
  writer_overhead/1000_cols/per_column_props     2.44 ms  (was   3.25 ms, −25%)
  writer_overhead/5000_cols/per_column_props    13.28 ms  (was  47.45 ms, −72%)
  writer_overhead/10000_cols/per_column_props   27.97 ms  (was 197.97 ms, −86%)
```

Scaling now linear.

# Are these changes tested?

All tests passing.

# Are there any user-facing changes?

None.

Signed-off-by: Hippolyte Barraud <hippolyte.barraud@datadoghq.com>
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>