ctsk commented on PR #7564:
URL: https://github.com/apache/arrow-rs/pull/7564#issuecomment-2918667539
<details>
<summary> Benchmark results </summary>
```
convert_columns 4096 u64(0)
time: [8.6248 µs 8.6292 µs 8.6342 µs]
change: [−37.960% −37.376% −36.828%] (p = 0.00 <
0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
2 (2.00%) high mild
12 (12.00%) high severe
convert_columns_prepared 4096 u64(0)
time: [8.7027 µs 8.7215 µs 8.7446 µs]
change: [−38.137% −37.873% −37.628%] (p = 0.00 <
0.05)
Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
4 (4.00%) high mild
convert_rows 4096 u64(0)
time: [33.664 µs 33.684 µs 33.708 µs]
change: [−2.3477% −1.9324% −1.5525%] (p = 0.00 <
0.05)
Performance has improved.
Found 16 outliers among 100 measurements (16.00%)
4 (4.00%) high mild
12 (12.00%) high severe
convert_columns 4096 u64(0.3)
time: [17.490 µs 17.508 µs 17.529 µs]
change: [−22.551% −22.332% −22.080%] (p = 0.00 <
0.05)
Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
5 (5.00%) high mild
6 (6.00%) high severe
convert_columns_prepared 4096 u64(0.3)
time: [17.185 µs 17.200 µs 17.217 µs]
change: [−23.545% −22.867% −22.376%] (p = 0.00 <
0.05)
Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
4 (4.00%) high mild
3 (3.00%) high severe
convert_rows 4096 u64(0.3)
time: [33.744 µs 33.771 µs 33.803 µs]
change: [−1.1265% −0.7677% −0.3875%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 18 outliers among 100 measurements (18.00%)
3 (3.00%) high mild
15 (15.00%) high severe
convert_columns 4096 i64(0)
time: [8.9686 µs 9.0007 µs 9.0306 µs]
change: [−38.392% −38.065% −37.720%] (p = 0.00 <
0.05)
Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
1 (1.00%) high mild
2 (2.00%) high severe
convert_columns_prepared 4096 i64(0)
time: [8.6245 µs 8.6571 µs 8.7058 µs]
change: [−39.865% −39.554% −39.245%] (p = 0.00 <
0.05)
Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
6 (6.00%) high mild
9 (9.00%) high severe
convert_rows 4096 i64(0)
time: [35.185 µs 35.203 µs 35.224 µs]
change: [−3.0149% −1.5765% −0.5948%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 16 outliers among 100 measurements (16.00%)
4 (4.00%) high mild
12 (12.00%) high severe
convert_columns 4096 i64(0.3)
time: [16.871 µs 16.894 µs 16.919 µs]
change: [−34.681% −34.243% −33.691%] (p = 0.00 <
0.05)
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
3 (3.00%) high mild
5 (5.00%) high severe
convert_columns_prepared 4096 i64(0.3)
time: [16.662 µs 16.696 µs 16.740 µs]
change: [−33.893% −33.650% −33.349%] (p = 0.00 <
0.05)
Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
3 (3.00%) high mild
6 (6.00%) high severe
convert_rows 4096 i64(0.3)
time: [35.174 µs 35.214 µs 35.263 µs]
change: [−0.9387% +0.0217% +1.7601%] (p = 0.98 >
0.05)
No change in performance detected.
Found 16 outliers among 100 measurements (16.00%)
1 (1.00%) low severe
2 (2.00%) high mild
13 (13.00%) high severe
convert_columns 4096 bool(0, 0.5)
time: [15.054 µs 15.066 µs 15.079 µs]
change: [−26.391% −26.084% −25.758%] (p = 0.00 <
0.05)
Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
6 (6.00%) high mild
9 (9.00%) high severe
convert_columns_prepared 4096 bool(0, 0.5)
time: [14.881 µs 14.891 µs 14.902 µs]
change: [−26.951% −26.691% −26.464%] (p = 0.00 <
0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
convert_rows 4096 bool(0, 0.5)
time: [18.083 µs 18.094 µs 18.107 µs]
change: [−4.1337% −3.5182% −3.0436%] (p = 0.00 <
0.05)
Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
4 (4.00%) high mild
6 (6.00%) high severe
convert_columns 4096 bool(0.3, 0.5)
time: [18.300 µs 18.326 µs 18.357 µs]
change: [−21.036% −20.693% −20.379%] (p = 0.00 <
0.05)
Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
3 (3.00%) high mild
8 (8.00%) high severe
convert_columns_prepared 4096 bool(0.3, 0.5)
time: [18.062 µs 18.077 µs 18.093 µs]
change: [−21.823% −21.670% −21.500%] (p = 0.00 <
0.05)
Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
4 (4.00%) high severe
convert_rows 4096 bool(0.3, 0.5)
time: [18.098 µs 18.109 µs 18.123 µs]
change: [−3.0894% −2.6045% −1.9644%] (p = 0.00 <
0.05)
Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
6 (6.00%) high mild
11 (11.00%) high severe
convert_columns 4096 string(10, 0)
time: [63.574 µs 63.616 µs 63.664 µs]
change: [−9.8826% −8.8928% −7.3140%] (p = 0.00 <
0.05)
Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
4 (4.00%) high mild
11 (11.00%) high severe
convert_columns_prepared 4096 string(10, 0)
time: [63.663 µs 63.695 µs 63.733 µs]
change: [−8.3089% −7.8557% −7.3498%] (p = 0.00 <
0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
convert_rows 4096 string(10, 0)
time: [71.260 µs 71.503 µs 71.927 µs]
change: [−0.1863% +0.2264% +0.7311%] (p = 0.37 >
0.05)
No change in performance detected.
Found 12 outliers among 100 measurements (12.00%)
2 (2.00%) high mild
10 (10.00%) high severe
convert_columns 4096 string(30, 0)
time: [64.286 µs 64.322 µs 64.362 µs]
change: [−8.8976% −7.8059% −5.8817%] (p = 0.00 <
0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
6 (6.00%) high mild
6 (6.00%) high severe
convert_columns_prepared 4096 string(30, 0)
time: [63.655 µs 63.869 µs 64.259 µs]
change: [−9.3644% −8.7082% −7.9615%] (p = 0.00 <
0.05)
Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
3 (3.00%) high mild
14 (14.00%) high severe
convert_rows 4096 string(30, 0)
time: [80.896 µs 81.570 µs 82.336 µs]
change: [+0.0781% +0.6149% +1.2358%] (p = 0.05 <
0.05)
Change within noise threshold.
Found 20 outliers among 100 measurements (20.00%)
5 (5.00%) high mild
15 (15.00%) high severe
convert_columns 4096 string(100, 0)
time: [92.732 µs 92.824 µs 92.933 µs]
change: [−4.2515% −3.8659% −3.4044%] (p = 0.00 <
0.05)
Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
3 (3.00%) high mild
10 (10.00%) high severe
convert_columns_prepared 4096 string(100, 0)
time: [92.247 µs 92.586 µs 92.952 µs]
change: [−6.9391% −6.3066% −5.4883%] (p = 0.00 <
0.05)
Performance has improved.
Found 2 outliers among 100 measurements (2.00%)
1 (1.00%) high mild
1 (1.00%) high severe
convert_rows 4096 string(100, 0)
time: [115.04 µs 115.14 µs 115.28 µs]
change: [−1.1380% −0.5042% +0.3602%] (p = 0.26 >
0.05)
No change in performance detected.
Found 13 outliers among 100 measurements (13.00%)
7 (7.00%) high mild
6 (6.00%) high severe
convert_columns 4096 string(100, 0.5)
time: [100.45 µs 100.56 µs 100.73 µs]
change: [−4.8758% −4.4574% −4.0861%] (p = 0.00 <
0.05)
Performance has improved.
Found 16 outliers among 100 measurements (16.00%)
3 (3.00%) high mild
13 (13.00%) high severe
convert_columns_prepared 4096 string(100, 0.5)
time: [100.55 µs 100.59 µs 100.64 µs]
change: [−3.2058% −2.4511% −1.4243%] (p = 0.00 <
0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
2 (2.00%) high mild
12 (12.00%) high severe
convert_rows 4096 string(100, 0.5)
time: [115.30 µs 115.44 µs 115.64 µs]
change: [−1.4128% −0.9677% −0.5774%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 13 outliers among 100 measurements (13.00%)
3 (3.00%) high mild
10 (10.00%) high severe
convert_columns 4096 string view(10, 0)
time: [64.267 µs 64.408 µs 64.685 µs]
change: [−9.9283% −9.0933% −8.2194%] (p = 0.00 <
0.05)
Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
4 (4.00%) high mild
7 (7.00%) high severe
convert_columns_prepared 4096 string view(10, 0)
time: [64.949 µs 64.979 µs 65.013 µs]
change: [−7.9519% −7.2841% −6.6567%] (p = 0.00 <
0.05)
Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
5 (5.00%) high mild
8 (8.00%) high severe
convert_rows 4096 string view(10, 0)
time: [83.003 µs 83.206 µs 83.596 µs]
change: [−0.8805% −0.2136% +0.4667%] (p = 0.57 >
0.05)
No change in performance detected.
Found 15 outliers among 100 measurements (15.00%)
3 (3.00%) high mild
12 (12.00%) high severe
convert_columns 4096 string view(30, 0)
time: [65.599 µs 65.666 µs 65.760 µs]
change: [−8.8254% −7.7019% −5.5487%] (p = 0.00 <
0.05)
Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
3 (3.00%) high mild
14 (14.00%) high severe
convert_columns_prepared 4096 string view(30, 0)
time: [66.005 µs 66.148 µs 66.373 µs]
change: [−7.8986% −7.4742% −6.8500%] (p = 0.00 <
0.05)
Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
2 (2.00%) low mild
3 (3.00%) high mild
13 (13.00%) high severe
convert_rows 4096 string view(30, 0)
time: [92.625 µs 92.716 µs 92.825 µs]
change: [+0.2072% +0.6132% +1.0647%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 17 outliers among 100 measurements (17.00%)
6 (6.00%) high mild
11 (11.00%) high severe
Benchmarking convert_columns 40960 string view(100, 0): Warming up for
3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase
target time to 5.6s, enable flat sampling, or reduce sample count to 60.
convert_columns 40960 string view(100, 0)
time: [1.0839 ms 1.0858 ms 1.0881 ms]
change: [−6.4563% −4.7634% −2.9791%] (p = 0.00 <
0.05)
Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
3 (3.00%) high mild
8 (8.00%) high severe
Benchmarking convert_columns_prepared 40960 string view(100, 0): Warming up
for 3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase
target time to 5.5s, enable flat sampling, or reduce sample count to 60.
convert_columns_prepared 40960 string view(100, 0)
time: [1.0905 ms 1.0921 ms 1.0940 ms]
change: [−6.5596% −3.6212% −0.2864%] (p = 0.02 <
0.05)
Change within noise threshold.
Found 10 outliers among 100 measurements (10.00%)
10 (10.00%) high severe
Benchmarking convert_rows 40960 string view(100, 0): Warming up for 3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase
target time to 8.1s, enable flat sampling, or reduce sample count to 50.
convert_rows 40960 string view(100, 0)
time: [1.6016 ms 1.6057 ms 1.6113 ms]
change: [−0.2298% +1.6819% +3.9067%] (p = 0.12 >
0.05)
No change in performance detected.
Found 13 outliers among 100 measurements (13.00%)
2 (2.00%) high mild
11 (11.00%) high severe
convert_columns 4096 string view(100, 0.5)
time: [97.439 µs 97.504 µs 97.574 µs]
change: [−8.8030% −8.5543% −8.1945%] (p = 0.00 <
0.05)
Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
2 (2.00%) high mild
8 (8.00%) high severe
convert_columns_prepared 4096 string view(100, 0.5)
time: [97.286 µs 97.369 µs 97.471 µs]
change: [−10.356% −8.8630% −7.8992%] (p = 0.00 <
0.05)
Performance has improved.
Found 16 outliers among 100 measurements (16.00%)
6 (6.00%) high mild
10 (10.00%) high severe
convert_rows 4096 string view(100, 0.5)
time: [126.99 µs 127.04 µs 127.11 µs]
change: [−2.2524% −0.4856% +0.8095%] (p = 0.64 >
0.05)
No change in performance detected.
Found 14 outliers among 100 measurements (14.00%)
2 (2.00%) high mild
12 (12.00%) high severe
convert_columns 4096 string_dictionary(10, 0)
time: [99.930 µs 99.986 µs 100.05 µs]
change: [−13.442% −10.922% −8.9707%] (p = 0.00 <
0.05)
Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
5 (5.00%) high mild
5 (5.00%) high severe
convert_columns_prepared 4096 string_dictionary(10, 0)
time: [97.489 µs 97.560 µs 97.654 µs]
change: [−9.7200% −9.3791% −9.0009%] (p = 0.00 <
0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
4 (4.00%) high mild
8 (8.00%) high severe
convert_rows 4096 string_dictionary(10, 0)
time: [71.240 µs 71.361 µs 71.557 µs]
change: [−1.8964% −1.0829% −0.3875%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 11 outliers among 100 measurements (11.00%)
3 (3.00%) high mild
8 (8.00%) high severe
convert_columns 4096 string_dictionary(30, 0)
time: [102.11 µs 102.17 µs 102.23 µs]
change: [−9.3297% −9.0212% −8.6683%] (p = 0.00 <
0.05)
Performance has improved.
Found 16 outliers among 100 measurements (16.00%)
4 (4.00%) high mild
12 (12.00%) high severe
convert_columns_prepared 4096 string_dictionary(30, 0)
time: [101.62 µs 101.78 µs 102.00 µs]
change: [−8.3852% −8.0843% −7.6847%] (p = 0.00 <
0.05)
Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
3 (3.00%) high mild
8 (8.00%) high severe
convert_rows 4096 string_dictionary(30, 0)
time: [80.250 µs 80.318 µs 80.405 µs]
change: [−0.4707% −0.1475% +0.2729%] (p = 0.45 >
0.05)
No change in performance detected.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
convert_columns 4096 string_dictionary(100, 0)
time: [158.86 µs 159.02 µs 159.18 µs]
change: [−7.4309% −6.9486% −6.4972%] (p = 0.00 <
0.05)
Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
5 (5.00%) high mild
4 (4.00%) high severe
convert_columns_prepared 4096 string_dictionary(100, 0)
time: [159.02 µs 159.16 µs 159.33 µs]
change: [−7.0098% −5.7656% −4.7319%] (p = 0.00 <
0.05)
Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
2 (2.00%) high mild
6 (6.00%) high severe
convert_rows 4096 string_dictionary(100, 0)
time: [115.44 µs 115.49 µs 115.55 µs]
change: [−0.5404% −0.0296% +0.5326%] (p = 0.93 >
0.05)
No change in performance detected.
Found 18 outliers among 100 measurements (18.00%)
5 (5.00%) high mild
13 (13.00%) high severe
convert_columns 4096 string_dictionary(100, 0.5)
time: [140.29 µs 140.37 µs 140.46 µs]
change: [−4.1150% −2.5329% −1.5660%] (p = 0.00 <
0.05)
Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
2 (2.00%) high mild
9 (9.00%) high severe
convert_columns_prepared 4096 string_dictionary(100, 0.5)
time: [138.95 µs 139.27 µs 139.88 µs]
change: [−2.4389% −1.6922% −1.0832%] (p = 0.00 <
0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
5 (5.00%) high mild
7 (7.00%) high severe
convert_rows 4096 string_dictionary(100, 0.5)
time: [115.64 µs 115.73 µs 115.87 µs]
change: [−1.0635% −0.8590% −0.6773%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 14 outliers among 100 measurements (14.00%)
6 (6.00%) high mild
8 (8.00%) high severe
convert_columns 4096 string_dictionary_low_cardinality(10, 0)
time: [34.553 µs 34.571 µs 34.593 µs]
change: [−12.758% −11.221% −10.294%] (p = 0.00 <
0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
5 (5.00%) high mild
7 (7.00%) high severe
convert_columns_prepared 4096 string_dictionary_low_cardinality(10, 0)
time: [33.344 µs 33.375 µs 33.415 µs]
change: [−12.529% −11.850% −11.076%] (p = 0.00 <
0.05)
Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
7 (7.00%) high mild
11 (11.00%) high severe
convert_rows 4096 string_dictionary_low_cardinality(10, 0)
time: [71.304 µs 71.488 µs 71.737 µs]
change: [−0.6645% −0.0751% +0.5889%] (p = 0.82 >
0.05)
No change in performance detected.
Found 18 outliers among 100 measurements (18.00%)
4 (4.00%) high mild
14 (14.00%) high severe
convert_columns 4096 string_dictionary_low_cardinality(30, 0)
time: [37.408 µs 37.466 µs 37.550 µs]
change: [−10.269% −8.6841% −6.7053%] (p = 0.00 <
0.05)
Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
2 (2.00%) high mild
8 (8.00%) high severe
convert_columns_prepared 4096 string_dictionary_low_cardinality(30, 0)
time: [36.662 µs 36.691 µs 36.731 µs]
change: [−8.7615% −8.3561% −7.8877%] (p = 0.00 <
0.05)
Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
3 (3.00%) high mild
14 (14.00%) high severe
convert_rows 4096 string_dictionary_low_cardinality(30, 0)
time: [80.417 µs 80.470 µs 80.533 µs]
change: [−3.4523% −1.4740% −0.0067%] (p = 0.10 >
0.05)
No change in performance detected.
Found 7 outliers among 100 measurements (7.00%)
2 (2.00%) high mild
5 (5.00%) high severe
convert_columns 4096 string_dictionary_low_cardinality(100, 0)
time: [60.507 µs 60.542 µs 60.582 µs]
change: [−15.770% −13.650% −11.777%] (p = 0.00 <
0.05)
Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
1 (1.00%) high mild
12 (12.00%) high severe
convert_columns_prepared 4096 string_dictionary_low_cardinality(100, 0)
time: [59.293 µs 59.349 µs 59.420 µs]
change: [−24.340% −21.689% −19.151%] (p = 0.00 <
0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
6 (6.00%) high mild
6 (6.00%) high severe
convert_rows 4096 string_dictionary_low_cardinality(100, 0)
time: [115.59 µs 115.65 µs 115.71 µs]
change: [−1.5510% −0.7109% −0.0310%] (p = 0.06 >
0.05)
No change in performance detected.
Found 14 outliers among 100 measurements (14.00%)
3 (3.00%) high mild
11 (11.00%) high severe
convert_columns 4096 string(20, 0.5), string(30, 0), string(100, 0), i64(0)
time: [271.17 µs 271.37 µs 271.68 µs]
change: [−0.7562% +0.3382% +1.6839%] (p = 0.69 >
0.05)
No change in performance detected.
Found 13 outliers among 100 measurements (13.00%)
2 (2.00%) high mild
11 (11.00%) high severe
convert_columns_prepared 4096 string(20, 0.5), string(30, 0), string(100,
0), i64(0)
time: [273.87 µs 275.05 µs 277.35 µs]
change: [−1.1562% −0.7121% −0.2446%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 14 outliers among 100 measurements (14.00%)
5 (5.00%) high mild
9 (9.00%) high severe
convert_rows 4096 string(20, 0.5), string(30, 0), string(100, 0), i64(0)
time: [331.04 µs 331.28 µs 331.59 µs]
change: [−1.9079% −1.5272% −1.1238%] (p = 0.00 <
0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
convert_columns 4096 4096 string_dictionary(20, 0.5), string_dictionary(30,
0), string_dictionary(10...
time: [394.81 µs 395.06 µs 395.33 µs]
change: [−5.5401% −5.0393% −4.4563%] (p = 0.00 <
0.05)
Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
5 (5.00%) high mild
7 (7.00%) high severe
convert_columns_prepared 4096 4096 string_dictionary(20, 0.5),
string_dictionary(30, 0), string_dict...
time: [390.39 µs 391.10 µs 392.09 µs]
change: [−5.9569% −5.3496% −4.6508%] (p = 0.00 <
0.05)
Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
4 (4.00%) high mild
10 (10.00%) high severe
convert_rows 4096 4096 string_dictionary(20, 0.5), string_dictionary(30, 0),
string_dictionary(100, ...
time: [331.13 µs 331.36 µs 331.60 µs]
change: [−0.1755% +0.2522% +0.6066%] (p = 0.23 >
0.05)
No change in performance detected.
Found 9 outliers among 100 measurements (9.00%)
5 (5.00%) high mild
4 (4.00%) high severe
iterate rows time: [29.031 µs 29.048 µs 29.068 µs]
change: [−1.2406% −0.7159% −0.2577%] (p = 0.00 <
0.05)
Change within noise threshold.
Found 18 outliers among 100 measurements (18.00%)
6 (6.00%) high mild
12 (12.00%) high severe
```
</details>
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
