Skip to content

POC: try using Arc<Vec<Buffer>> instead of Arc<[Buffer]> #7804

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 11 commits into
base: main
Choose a base branch
from
Draft

POC: try using Arc<Vec<Buffer>> instead of Arc<[Buffer]> #7804

wants to merge 11 commits into from

Conversation

alamb
Copy link
Contributor

@alamb alamb commented Jun 27, 2025

This is an experiment built on top of @ctsk 's PR here: #7773

The idea is to just use the Vec directly rather than discarding the vec overhead. This change is in

I will run benchmarks against this PR and see how they look compared to

@github-actions github-actions bot added the arrow Changes to the arrow crate label Jun 27, 2025
@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖 ./gh_compare_arrow.sh Benchmark Script Running
Linux aal-dev 6.11.0-1015-gcp #15~24.04.1-Ubuntu SMP Thu Apr 24 20:41:05 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/try_just_arc_vec (180636b) to e42df82 diff
BENCH_NAME=view_types
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental --bench view_types
BENCH_FILTER=
BENCH_BRANCH_NAME=alamb_try_just_arc_vec
Results will be posted here when complete

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖: Benchmark completed

Details 

group                       alamb_try_just_arc_vec                 main
-----                       ----------------------                 ----
gc view types all           1.01    858.4±2.44µs        ? ?/sec    1.00    848.5±1.60µs        ? ?/sec
gc view types slice half    1.01    426.9±1.52µs        ? ?/sec    1.00    420.9±1.48µs        ? ?/sec
view types slice            1.00    633.5±6.75ns        ? ?/sec    1.11    706.0±0.59ns        ? ?/sec

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖 ./gh_compare_arrow.sh Benchmark Script Running
Linux aal-dev 6.11.0-1015-gcp #15~24.04.1-Ubuntu SMP Thu Apr 24 20:41:05 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/try_just_arc_vec (180636b) to e42df82 diff
BENCH_NAME=concatenate_kernel
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental --bench concatenate_kernel
BENCH_FILTER=
BENCH_BRANCH_NAME=alamb_try_just_arc_vec
Results will be posted here when complete

Dandandan
Dandandan reviewed Jun 27, 2025
View reviewed changes
arrow-array/src/view_buffers.rs
/// Convertes this ViewBuffers into a Vec<Buffer>, cloning the underlying buffers if
/// they are shared.
pub fn unwrap_or_clone(self) -> Vec<Buffer> {
Arc::unwrap_or_clone(self.0)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah this is nice.

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖: Benchmark completed

Details 

group                                                          alamb_try_just_arc_vec                 main
-----                                                          ----------------------                 ----
concat 1024 arrays boolean 4                                   1.00     27.4±0.04µs        ? ?/sec    1.05     28.8±0.04µs        ? ?/sec
concat 1024 arrays i32 4                                       1.00     13.0±0.04µs        ? ?/sec    1.22     15.8±0.03µs        ? ?/sec
concat 1024 arrays str 4                                       1.00     56.5±1.11µs        ? ?/sec    1.01     57.1±0.28µs        ? ?/sec
concat boolean 1024                                            1.00    417.8±2.95ns        ? ?/sec    1.01    421.8±0.65ns        ? ?/sec
concat boolean 8192 over 100 arrays                            1.00     50.8±0.11µs        ? ?/sec    1.00     50.8±0.08µs        ? ?/sec
concat boolean nulls 1024                                      1.00    746.7±1.37ns        ? ?/sec    1.04    779.0±1.11ns        ? ?/sec
concat boolean nulls 8192 over 100 arrays                      1.00    109.6±0.14µs        ? ?/sec    1.00    109.5±0.16µs        ? ?/sec
concat fixed size lists                                        1.00   749.1±17.18µs        ? ?/sec    1.21   903.7±48.42µs        ? ?/sec
concat i32 1024                                                1.01    444.7±0.84ns        ? ?/sec    1.00    441.8±0.67ns        ? ?/sec
concat i32 8192 over 100 arrays                                1.00   210.7±10.25µs        ? ?/sec    1.03    217.9±3.91µs        ? ?/sec
concat i32 nulls 1024                                          1.00    748.9±1.23ns        ? ?/sec    1.02    760.4±1.45ns        ? ?/sec
concat i32 nulls 8192 over 100 arrays                          1.00    282.4±9.54µs        ? ?/sec    1.01   284.9±10.88µs        ? ?/sec
concat str 1024                                                1.04     14.0±1.11µs        ? ?/sec    1.00     13.4±1.07µs        ? ?/sec
concat str 8192 over 100 arrays                                1.00    105.7±0.65ms        ? ?/sec    1.03    108.5±1.39ms        ? ?/sec
concat str nulls 1024                                          1.07      6.9±0.64µs        ? ?/sec    1.00      6.5±0.65µs        ? ?/sec
concat str nulls 8192 over 100 arrays                          1.00     52.2±0.59ms        ? ?/sec    1.03     53.9±0.60ms        ? ?/sec
concat str_dict 1024                                           1.00      3.0±0.01µs        ? ?/sec    1.00      3.0±0.01µs        ? ?/sec
concat str_dict_sparse 1024                                    1.00      6.9±0.03µs        ? ?/sec    1.01      7.0±0.03µs        ? ?/sec
concat struct with int32 and dicts size=1024 count=2           1.00      7.0±0.16µs        ? ?/sec    1.03      7.2±0.02µs        ? ?/sec
concat utf8_view  max_str_len=128 null_density=0               1.00     77.4±0.47µs        ? ?/sec    1.01     78.5±0.56µs        ? ?/sec
concat utf8_view  max_str_len=128 null_density=0.2             1.00     83.8±0.40µs        ? ?/sec    1.01     84.9±0.75µs        ? ?/sec
concat utf8_view  max_str_len=20 null_density=0                1.18     90.9±0.30µs        ? ?/sec    1.00     77.3±0.40µs        ? ?/sec
concat utf8_view  max_str_len=20 null_density=0.2              1.15     97.3±0.32µs        ? ?/sec    1.00     84.5±0.61µs        ? ?/sec
concat utf8_view all_inline max_str_len=12 null_density=0      1.25     48.0±3.28µs        ? ?/sec    1.00     38.5±2.52µs        ? ?/sec
concat utf8_view all_inline max_str_len=12 null_density=0.2    1.16     55.0±3.08µs        ? ?/sec    1.00     47.2±3.03µs        ? ?/sec

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖 ./gh_compare_arrow.sh Benchmark Script Running
Linux aal-dev 6.11.0-1015-gcp #15~24.04.1-Ubuntu SMP Thu Apr 24 20:41:05 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/try_just_arc_vec (180636b) to e42df82 diff
BENCH_NAME=coalesce_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental --bench coalesce_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=alamb_try_just_arc_vec
Results will be posted here when complete

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

Weirdly this still shows a slow down for concat

concat utf8_view  max_str_len=20 null_density=0                1.18     90.9±0.30µs        ? ?/sec    1.00     77.3±0.40µs        ? ?/sec
concat utf8_view  max_str_len=20 null_density=0.2              1.15     97.3±0.32µs        ? ?/sec    1.00     84.5±0.61µs        ? ?/sec
concat utf8_view all_inline max_str_len=12 null_density=0      1.25     48.0±3.28µs        ? ?/sec    1.00     38.5±2.52µs        ? ?/sec
concat utf8_view all_inline max_str_len=12 null_density=0.2    1.16     55.0±3.08µs        ? ?/sec    1.00     47.2±3.03µs        ? ?/sec

🤔

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖: Benchmark completed

Details 

group                                                                                alamb_try_just_arc_vec                 main
-----                                                                                ----------------------                 ----
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.001                               1.00    257.4±2.55ms        ? ?/sec    1.02    261.5±2.62ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.01                                1.01      9.2±0.19ms        ? ?/sec    1.00      9.1±0.10ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.1                                 1.04      4.6±0.13ms        ? ?/sec    1.00      4.4±0.13ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0, selectivity: 0.8                                 1.00      3.6±0.07ms        ? ?/sec    1.00      3.6±0.05ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.001                             1.02    257.2±3.38ms        ? ?/sec    1.00    251.7±3.30ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.01                              1.00     10.2±0.11ms        ? ?/sec    1.03     10.5±0.10ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.1                               1.00      4.7±0.18ms        ? ?/sec    1.04      4.9±0.14ms        ? ?/sec
filter: mixed_dict, 8192, nulls: 0.1, selectivity: 0.8                               1.00      4.6±0.05ms        ? ?/sec    1.05      4.8±0.09ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.001                               1.00     60.7±3.16ms        ? ?/sec    1.00     60.6±0.29ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.01                                1.00     12.1±0.14ms        ? ?/sec    1.02     12.4±0.18ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.1                                 1.03     11.0±0.57ms        ? ?/sec    1.00     10.7±0.65ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0, selectivity: 0.8                                 1.09      9.4±0.28ms        ? ?/sec    1.00      8.7±0.39ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.001                             1.00     80.5±1.52ms        ? ?/sec    1.03     82.8±1.31ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.01                              1.01     14.2±0.16ms        ? ?/sec    1.00     14.0±0.26ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.1                               1.00     10.6±0.36ms        ? ?/sec    1.00     10.5±0.46ms        ? ?/sec
filter: mixed_utf8, 8192, nulls: 0.1, selectivity: 0.8                               1.02     10.5±0.23ms        ? ?/sec    1.00     10.3±0.27ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.001      1.00     48.0±0.26ms        ? ?/sec    1.02     49.0±0.22ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.01       1.00      6.2±0.06ms        ? ?/sec    1.01      6.2±0.08ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.1        1.04      5.2±0.21ms        ? ?/sec    1.00      5.0±0.31ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0, selectivity: 0.8        1.02      3.3±0.09ms        ? ?/sec    1.00      3.2±0.07ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.001    1.00     62.4±0.68ms        ? ?/sec    1.01     63.3±0.31ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.01     1.00      8.6±0.08ms        ? ?/sec    1.03      8.9±0.08ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.1      1.00      5.5±0.13ms        ? ?/sec    1.07      5.9±0.16ms        ? ?/sec
filter: mixed_utf8view (max_string_len=128), 8192, nulls: 0.1, selectivity: 0.8      1.00      3.9±0.02ms        ? ?/sec    1.04      4.0±0.03ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.001       1.00     41.5±0.17ms        ? ?/sec    1.04     43.2±0.15ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.01        1.00      4.9±0.03ms        ? ?/sec    1.01      4.9±0.02ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.1         1.00      2.8±0.17ms        ? ?/sec    1.01      2.8±0.19ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0, selectivity: 0.8         1.00      2.4±0.02ms        ? ?/sec    1.00      2.4±0.03ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.001     1.00     55.3±0.24ms        ? ?/sec    1.03     57.0±0.13ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.01      1.00      7.5±0.04ms        ? ?/sec    1.03      7.7±0.03ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.1       1.00      3.7±0.20ms        ? ?/sec    1.08      3.9±0.06ms        ? ?/sec
filter: mixed_utf8view (max_string_len=20), 8192, nulls: 0.1, selectivity: 0.8       1.00      4.6±0.03ms        ? ?/sec    1.03      4.7±0.02ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.001                          1.00     64.2±0.20ms        ? ?/sec    1.03     66.2±0.14ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.01                           1.00      7.7±0.04ms        ? ?/sec    1.05      8.1±0.02ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.1                            1.03      4.8±0.22ms        ? ?/sec    1.00      4.7±0.23ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0, selectivity: 0.8                            1.01      3.9±0.03ms        ? ?/sec    1.00      3.8±0.03ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.001                        1.00     80.9±0.16ms        ? ?/sec    1.13     91.2±0.20ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.01                         1.00     11.4±0.05ms        ? ?/sec    1.03     11.8±0.04ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.1                          1.02      6.4±0.22ms        ? ?/sec    1.00      6.3±0.16ms        ? ?/sec
filter: single_utf8view, 8192, nulls: 0.1, selectivity: 0.8                          1.00      6.0±0.04ms        ? ?/sec    1.06      6.3±0.13ms        ? ?/sec

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖 ./gh_compare_arrow.sh Benchmark Script Running
Linux aal-dev 6.11.0-1015-gcp #15~24.04.1-Ubuntu SMP Thu Apr 24 20:41:05 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
Comparing alamb/try_just_arc_vec (180636b) to e42df82 diff
BENCH_NAME=filter_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental --bench filter_kernels
BENCH_FILTER=
BENCH_BRANCH_NAME=alamb_try_just_arc_vec
Results will be posted here when complete

@alamb
Copy link
Contributor Author

alamb commented Jun 27, 2025

🤖: Benchmark completed

Details 

group                                                                         alamb_try_just_arc_vec                 main
-----                                                                         ----------------------                 ----
filter context decimal128 (kept 1/2)                                          1.00     43.1±7.28µs        ? ?/sec    1.09     46.9±7.96µs        ? ?/sec
filter context decimal128 high selectivity (kept 1023/1024)                   1.03     51.0±1.82µs        ? ?/sec    1.00     49.7±1.10µs        ? ?/sec
filter context decimal128 low selectivity (kept 1/1024)                       1.05    255.7±0.28ns        ? ?/sec    1.00    243.1±0.22ns        ? ?/sec
filter context f32 (kept 1/2)                                                 1.00     62.5±0.11µs        ? ?/sec    1.57     98.0±0.26µs        ? ?/sec
filter context f32 high selectivity (kept 1023/1024)                          1.00     13.4±0.39µs        ? ?/sec    1.02     13.7±0.44µs        ? ?/sec
filter context f32 low selectivity (kept 1/1024)                              1.00    434.8±0.42ns        ? ?/sec    1.11    484.1±0.40ns        ? ?/sec
filter context fsb with value length 20 (kept 1/2)                            1.00     42.5±0.16µs        ? ?/sec    1.67     71.0±0.12µs        ? ?/sec
filter context fsb with value length 20 high selectivity (kept 1023/1024)     1.00     42.4±0.11µs        ? ?/sec    1.67     70.9±0.19µs        ? ?/sec
filter context fsb with value length 20 low selectivity (kept 1/1024)         1.00     42.4±0.10µs        ? ?/sec    1.67     70.9±0.09µs        ? ?/sec
filter context fsb with value length 5 (kept 1/2)                             1.00     42.5±0.13µs        ? ?/sec    1.67     71.0±0.33µs        ? ?/sec
filter context fsb with value length 5 high selectivity (kept 1023/1024)      1.00     42.4±0.07µs        ? ?/sec    1.68     71.3±0.66µs        ? ?/sec
filter context fsb with value length 5 low selectivity (kept 1/1024)          1.00     42.4±0.11µs        ? ?/sec    1.67     70.9±0.13µs        ? ?/sec
filter context fsb with value length 50 (kept 1/2)                            1.00     42.5±0.07µs        ? ?/sec    1.67     70.9±0.15µs        ? ?/sec
filter context fsb with value length 50 high selectivity (kept 1023/1024)     1.00     42.4±0.05µs        ? ?/sec    1.67     70.9±0.13µs        ? ?/sec
filter context fsb with value length 50 low selectivity (kept 1/1024)         1.00     42.5±1.14µs        ? ?/sec    1.67     70.9±0.11µs        ? ?/sec
filter context i32 (kept 1/2)                                                 1.00     22.7±0.05µs        ? ?/sec    1.00     22.6±0.07µs        ? ?/sec
filter context i32 high selectivity (kept 1023/1024)                          1.03      6.5±0.43µs        ? ?/sec    1.00      6.3±0.40µs        ? ?/sec
filter context i32 low selectivity (kept 1/1024)                              1.03    249.7±0.29ns        ? ?/sec    1.00    243.3±1.05ns        ? ?/sec
filter context i32 w NULLs (kept 1/2)                                         1.00     65.4±0.12µs        ? ?/sec    1.44     94.1±0.25µs        ? ?/sec
filter context i32 w NULLs high selectivity (kept 1023/1024)                  1.00     13.8±0.69µs        ? ?/sec    1.00     13.7±0.41µs        ? ?/sec
filter context i32 w NULLs low selectivity (kept 1/1024)                      1.00    440.6±0.87ns        ? ?/sec    1.07   472.6±11.28ns        ? ?/sec
filter context mixed string view (kept 1/2)                                   1.00     84.4±1.22µs        ? ?/sec    1.38    116.3±5.58µs        ? ?/sec
filter context mixed string view high selectivity (kept 1023/1024)            1.00     58.4±1.31µs        ? ?/sec    1.02     59.4±1.18µs        ? ?/sec
filter context mixed string view low selectivity (kept 1/1024)                1.00    669.4±1.61ns        ? ?/sec    1.00    670.5±0.98ns        ? ?/sec
filter context short string view (kept 1/2)                                   1.00     86.0±5.98µs        ? ?/sec    1.40    120.4±5.90µs        ? ?/sec
filter context short string view high selectivity (kept 1023/1024)            1.00     58.2±1.60µs        ? ?/sec    1.02     59.2±1.30µs        ? ?/sec
filter context short string view low selectivity (kept 1/1024)                1.00    485.7±0.62ns        ? ?/sec    1.01    492.3±1.96ns        ? ?/sec
filter context string (kept 1/2)                                              1.00   562.6±15.04µs        ? ?/sec    1.06   593.7±12.09µs        ? ?/sec
filter context string dictionary (kept 1/2)                                   1.00     23.2±0.06µs        ? ?/sec    1.01     23.4±0.05µs        ? ?/sec
filter context string dictionary high selectivity (kept 1023/1024)            1.00      7.1±0.31µs        ? ?/sec    1.03      7.3±0.45µs        ? ?/sec
filter context string dictionary low selectivity (kept 1/1024)                1.00    819.8±1.66ns        ? ?/sec    1.01    827.0±4.78ns        ? ?/sec
filter context string dictionary w NULLs (kept 1/2)                           1.00     66.2±0.21µs        ? ?/sec    1.43     94.7±0.24µs        ? ?/sec
filter context string dictionary w NULLs high selectivity (kept 1023/1024)    1.00     14.3±0.37µs        ? ?/sec    1.03     14.8±0.45µs        ? ?/sec
filter context string dictionary w NULLs low selectivity (kept 1/1024)        1.00   1027.5±0.92ns        ? ?/sec    1.04   1073.6±7.43ns        ? ?/sec
filter context string high selectivity (kept 1023/1024)                       1.04    661.7±6.21µs        ? ?/sec    1.00   636.3±15.85µs        ? ?/sec
filter context string low selectivity (kept 1/1024)                           1.00    962.2±8.97ns        ? ?/sec    1.17   1124.7±2.58ns        ? ?/sec
filter context u8 (kept 1/2)                                                  1.00     18.8±0.03µs        ? ?/sec    1.00     18.9±0.04µs        ? ?/sec
filter context u8 high selectivity (kept 1023/1024)                           1.00  1821.0±10.29ns        ? ?/sec    1.02  1856.8±14.36ns        ? ?/sec
filter context u8 low selectivity (kept 1/1024)                               1.00    238.7±0.23ns        ? ?/sec    1.01    240.1±0.95ns        ? ?/sec
filter context u8 w NULLs (kept 1/2)                                          1.00     61.9±0.46µs        ? ?/sec    1.46     90.1±0.18µs        ? ?/sec
filter context u8 w NULLs high selectivity (kept 1023/1024)                   1.00      8.5±0.02µs        ? ?/sec    1.04      8.9±0.03µs        ? ?/sec
filter context u8 w NULLs low selectivity (kept 1/1024)                       1.00    434.9±0.99ns        ? ?/sec    1.29    562.5±0.85ns        ? ?/sec
filter decimal128 (kept 1/2)                                                  1.00     95.5±0.26µs        ? ?/sec    1.01     96.9±0.39µs        ? ?/sec
filter decimal128 high selectivity (kept 1023/1024)                           1.00     52.6±1.22µs        ? ?/sec    1.02     53.4±1.64µs        ? ?/sec
filter decimal128 low selectivity (kept 1/1024)                               1.24      3.0±0.00µs        ? ?/sec    1.00      2.4±0.00µs        ? ?/sec
filter f32 (kept 1/2)                                                         1.29    252.4±0.84µs        ? ?/sec    1.00    196.3±0.30µs        ? ?/sec
filter fsb with value length 20 (kept 1/2)                                    1.00    134.8±0.57µs        ? ?/sec    1.11    149.4±0.45µs        ? ?/sec
filter fsb with value length 20 high selectivity (kept 1023/1024)             1.03     72.1±2.29µs        ? ?/sec    1.00     69.8±2.48µs        ? ?/sec
filter fsb with value length 20 low selectivity (kept 1/1024)                 1.24      3.2±0.01µs        ? ?/sec    1.00      2.5±0.00µs        ? ?/sec
filter fsb with value length 5 (kept 1/2)                                     1.00    131.7±0.32µs        ? ?/sec    1.16    152.8±0.42µs        ? ?/sec
filter fsb with value length 5 high selectivity (kept 1023/1024)              1.00     11.0±0.62µs        ? ?/sec    1.02     11.2±0.47µs        ? ?/sec
filter fsb with value length 5 low selectivity (kept 1/1024)                  1.25      3.1±0.01µs        ? ?/sec    1.00      2.5±0.00µs        ? ?/sec
filter fsb with value length 50 (kept 1/2)                                    1.01    193.9±7.95µs        ? ?/sec    1.00    192.9±7.57µs        ? ?/sec
filter fsb with value length 50 high selectivity (kept 1023/1024)             1.01    212.7±7.92µs        ? ?/sec    1.00    210.1±7.30µs        ? ?/sec
filter fsb with value length 50 low selectivity (kept 1/1024)                 1.24      3.2±0.00µs        ? ?/sec    1.00      2.6±0.01µs        ? ?/sec
filter i32 (kept 1/2)                                                         1.02     93.5±0.14µs        ? ?/sec    1.00     91.7±0.14µs        ? ?/sec
filter i32 high selectivity (kept 1023/1024)                                  1.01      8.6±0.38µs        ? ?/sec    1.00      8.5±0.34µs        ? ?/sec
filter i32 low selectivity (kept 1/1024)                                      1.28      3.1±0.01µs        ? ?/sec    1.00      2.4±0.01µs        ? ?/sec
filter optimize (kept 1/2)                                                    1.15     95.4±1.67µs        ? ?/sec    1.00     82.9±0.19µs        ? ?/sec
filter optimize high selectivity (kept 1023/1024)                             1.00      2.8±0.01µs        ? ?/sec    1.13      3.2±0.01µs        ? ?/sec
filter optimize low selectivity (kept 1/1024)                                 1.29      2.8±0.01µs        ? ?/sec    1.00      2.2±0.01µs        ? ?/sec
filter run array (kept 1/2)                                                   1.19    446.0±0.90µs        ? ?/sec    1.00    374.1±0.98µs        ? ?/sec
filter run array high selectivity (kept 1023/1024)                            1.15    396.3±1.41µs        ? ?/sec    1.00    343.3±1.63µs        ? ?/sec
filter run array low selectivity (kept 1/1024)                                1.35    332.7±0.84µs        ? ?/sec    1.00    246.4±2.33µs        ? ?/sec
filter single record batch                                                    1.03     95.5±0.14µs        ? ?/sec    1.00     92.3±0.20µs        ? ?/sec
filter u8 (kept 1/2)                                                          1.02     93.7±0.18µs        ? ?/sec    1.00     92.1±0.29µs        ? ?/sec
filter u8 high selectivity (kept 1023/1024)                                   1.00      3.8±0.02µs        ? ?/sec    1.05      4.0±0.02µs        ? ?/sec
filter u8 low selectivity (kept 1/1024)                                       1.22      3.0±0.01µs        ? ?/sec    1.00      2.5±0.01µs        ? ?/sec

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Dandandan Dandandan Dandandan left review comments

Assignees
No one assigned
Labels
arrow Changes to the arrow crate
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@alamb @Dandandan @ShiKaiWi @ctsk
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy