Parquet page size mid batch
#12Comparing
parquet-page-size-mid-batch
(0b13cb9
) withmain
(2dc7a67
)-31%
- Improvement
- 4
- Regression
- 4
- Untouched
- 600
- New
- 13
- Skipped
- 2169
This run is associated to a commit that was force-pushed
It will not be associated with its branch history. Be careful when comparing its performance to other runs.No successful run was found on main ( 48fa8a7) during the generation of this report, so 2dc7a67 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.
Benchmarks
2169 total
The benchmarks below were skipped, so their baseline results are used instead. If they were deleted in your codebase, archive them to remove them from the performance reports.
Learn more about archiving benchmarks
Learn more about archiving benchmarks
or
arrow/benches/buffer_bit_ops.rs::benches::bit_ops_benchmark::buffer_binary_opsSkipped
11.3 µs*
not_with_offset
arrow/benches/buffer_bit_ops.rs::benches::bit_ops_benchmark::buffer_unary_opsSkipped
8.5 µs*
or_with_offset
arrow/benches/buffer_bit_ops.rs::benches::bit_ops_benchmark::buffer_binary_opsSkipped
16.7 µs*
not
arrow/benches/buffer_bit_ops.rs::benches::bit_ops_benchmark::buffer_unary_opsSkipped
8.4 µs*
and
arrow/benches/buffer_bit_ops.rs::benches::bit_ops_benchmark::buffer_binary_opsSkipped
11 µs*
and_with_offset
arrow/benches/buffer_bit_ops.rs::benches::bit_ops_benchmark::buffer_binary_opsSkipped
16.7 µs*
project[1000x8192 -> 500x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
85.9 µs*
project[1000x8192 -> 999x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
167.1 µs*
project[100x8192 -> 1x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
4.5 µs*
project[10x8192 -> 5x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
8.2 µs*
project[1000x8192 -> 1x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
4.5 µs*
project[100x8192 -> 50x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
16.6 µs*
project[10x8192 -> 9x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
9.6 µs*
project[100x8192 -> 99x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
23.3 µs*
project[10x8192 -> 1x8192]
arrow-array/benches/record_batch.rs::benches::criterion_benchmarkSkipped
4.6 µs*
StreamWriter/write_10/zstd
arrow-ipc/benches/ipc_writer.rs::benches::criterion_benchmark::arrow_ipc_stream_writerSkipped
43.7 ms*
StreamWriter/write_10
arrow-ipc/benches/ipc_writer.rs::benches::criterion_benchmark::arrow_ipc_stream_writerSkipped
9.7 ms*
FileWriter/write_10
arrow-ipc/benches/ipc_writer.rs::benches::criterion_benchmark::arrow_ipc_stream_writerSkipped
10.7 ms*
occupancy(values: 10, occupancy: 0.1, null_percent: 0)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
8.7 µs*
occupancy(values: 10, occupancy: 0.1, null_percent: 0.1)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
15.7 µs*
occupancy(values: 100, occupancy: 0.5, null_percent: 0.9)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
5.9 µs*
occupancy(values: 10, occupancy: 0.1, null_percent: 0.5)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
9.1 µs*
occupancy(values: 100, occupancy: 1, null_percent: 0)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
8.7 µs*
occupancy(values: 512, occupancy: 0.5, null_percent: 0.5)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
8.9 µs*
occupancy(values: 100, occupancy: 1, null_percent: 0.1)
arrow-array/benches/occupancy.rs::benches::criterion_benchmarkSkipped
14.2 µs*
Commits
Click on a commit to change the comparison rangeBase
main
2dc7a67
-30.6%
perf(parquet): mark cold paths #[cold] so they move out of hot icache
0b13cb9
3 months ago
by adriangb