mkleen commented on code in PR #11285:
URL: https://github.com/apache/arrow-rs/pull/11285#discussion_r4146263175
##########
parquet/benches/arrow_statistics.rs:
##########
@@ -347,33 +342,18 @@ fn page_index_benchmark(c: &mut Criterion) {
(num_pages, &data[range.start as usize..range.end as usize])
})
.collect();
- let row_group_indices: Vec<usize> = (0..row_groups).collect();
- let num_columns = reader.parquet_schema().num_columns();
let mut group = c.benchmark_group(format!(
"Decode page index statistics for {data_type} ({} pages)",
column_indexes.iter().map(|(n, _)| n).sum::<usize>()
));
group.bench_function("full page index", |b| {
b.iter(|| {
- let mut builder = PageIndexBuilder::new(row_groups,
num_columns);
- for (rg, (_, bytes)) in column_indexes.iter().enumerate() {
- let index = decode_column_index(bytes,
physical_type).unwrap();
- builder.put_column_index(index, rg, column);
- }
- let page_index = builder.build();
- let _ = converter
- .data_page_mins(&page_index, &row_group_indices)
- .unwrap();
- let _ = converter
- .data_page_maxes(&page_index, &row_group_indices)
- .unwrap();
- let _ = converter
- .data_page_null_counts(&page_index, &row_group_indices)
- .unwrap();
- let _ = converter
- .data_page_nan_counts(&page_index, &row_group_indices)
- .unwrap();
+ converter
Review Comment:
This measures `data_page_statistics_from_bytes` against `data_page_mins`,
`data_page_maxes`, `data_page_null_counts` and `data_page_nan_counts`. So i
think this is a fair comparision.
--
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]
