Skip to content
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.

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

feat(services/memory): migrate service memory #2229

Merged
merged 2 commits into from
May 8, 2023

Conversation

PsiACE
Copy link
Member

@PsiACE PsiACE commented May 8, 2023

PsiACE added 2 commits May 8, 2023 11:48
Signed-off-by: Chojan Shang <psiace@apache.org>
Signed-off-by: Chojan Shang <psiace@apache.org>
@Xuanwo
Copy link
Member

Xuanwo commented May 8, 2023

Show some benchmarks 🚀, the benchmark itself seems unstable.

service_memory_read_full/4.00 KiB
                        time:   [952.53 ns 952.77 ns 953.02 ns]
                        thrpt:  [4.0028 GiB/s 4.0038 GiB/s 4.0048 GiB/s]
                 change:
                        time:   [-7.6826% -7.4576% -7.2313%] (p = 0.00 < 0.05)
                        thrpt:  [+7.7950% +8.0585% +8.3219%]
                        Performance has improved.
service_memory_read_full/256 KiB
                        time:   [65.307 µs 65.558 µs 65.765 µs]
                        thrpt:  [3.7123 GiB/s 3.7241 GiB/s 3.7383 GiB/s]
                 change:
                        time:   [+573.28% +579.84% +586.81%] (p = 0.00 < 0.05)
                        thrpt:  [-85.440% -85.291% -85.147%]
                        Performance has regressed.
service_memory_read_full/4.00 MiB
                        time:   [1.0436 ms 1.0446 ms 1.0457 ms]
                        thrpt:  [3.7357 GiB/s 3.7396 GiB/s 3.7432 GiB/s]
                 change:
                        time:   [+717.03% +722.26% +727.62%] (p = 0.00 < 0.05)
                        thrpt:  [-87.917% -87.838% -87.761%]
                        Performance has regressed.
service_memory_read_full/16.0 MiB
                        time:   [214.32 µs 215.09 µs 215.77 µs]
                        thrpt:  [72.415 GiB/s 72.645 GiB/s 72.905 GiB/s]
                 change:
                        time:   [-71.389% -71.098% -70.840%] (p = 0.00 < 0.05)
                        thrpt:  [+242.93% +245.99% +249.52%]
                        Performance has improved.

service_memory_read_part/4.00 KiB
                        time:   [993.14 ns 995.71 ns 998.68 ns]
                        thrpt:  [3.8197 GiB/s 3.8311 GiB/s 3.8411 GiB/s]
                 change:
                        time:   [-9.5393% -9.2148% -8.9114%] (p = 0.00 < 0.05)
                        thrpt:  [+9.7832% +10.150% +10.545%]
                        Performance has improved.
service_memory_read_part/256 KiB
                        time:   [95.243 µs 95.276 µs 95.317 µs]
                        thrpt:  [2.5614 GiB/s 2.5625 GiB/s 2.5633 GiB/s]
                 change:
                        time:   [+277.54% +277.78% +278.01%] (p = 0.00 < 0.05)
                        thrpt:  [-73.546% -73.529% -73.513%]
                        Performance has regressed.
service_memory_read_part/4.00 MiB
                        time:   [95.918 µs 95.975 µs 96.044 µs]
                        thrpt:  [40.672 GiB/s 40.701 GiB/s 40.725 GiB/s]
                 change:
                        time:   [-73.025% -72.757% -72.505%] (p = 0.00 < 0.05)
                        thrpt:  [+263.70% +267.07% +270.72%]
                        Performance has improved.
service_memory_read_part/16.0 MiB
                        time:   [6.0835 ms 6.0844 ms 6.0854 ms]
                        thrpt:  [2.5676 GiB/s 2.5680 GiB/s 2.5684 GiB/s]
                 change:
                        time:   [-4.5343% -3.4569% -2.5650%] (p = 0.00 < 0.05)
                        thrpt:  [+2.6325% +3.5807% +4.7497%]
                        Performance has improved.

@Xuanwo Xuanwo merged commit 69a8e4e into apache:main May 8, 2023
@PsiACE
Copy link
Member Author

PsiACE commented May 8, 2023

❯ OPENDAL_MEMORY_TEST=on cargo bench memory
   Compiling opendal v0.33.3 (/home/psiace/work/opendal/core)
    Finished bench [optimized + debuginfo] target(s) in 36.77s
     Running benches/ops/main.rs (target/release/deps/ops-e7473ef0bfcb44a7)
fs not set, ignore
s3 not set, ignore
Benchmarking service_memory_read_full/4.00 KiB: Collecting 100 samples in
service_memory_read_full/4.00 KiB
                        time:   [1.4364 µs 1.4526 µs 1.4750 µs]
                        thrpt:  [2.5863 GiB/s 2.6261 GiB/s 2.6557 GiB/s]
                 change:
                        time:   [-11.284% -9.4380% -7.5256%] (p = 0.00 < 0.05)
                        thrpt:  [+8.1381% +10.422% +12.719%]
                        Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
  4 (4.00%) high mild
  11 (11.00%) high severe
Benchmarking service_memory_read_full/256 KiB: Collecting 100 samples in 
service_memory_read_full/256 KiB
                        time:   [8.4487 µs 8.6364 µs 8.8721 µs]
                        thrpt:  [27.518 GiB/s 28.269 GiB/s 28.897 GiB/s]
                 change:
                        time:   [-51.361% -50.000% -48.568%] (p = 0.00 < 0.05)
                        thrpt:  [+94.430% +99.999% +105.60%]
                        Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
  4 (4.00%) high mild
  13 (13.00%) high severe
Benchmarking service_memory_read_full/4.00 MiB: Collecting 100 samples in
service_memory_read_full/4.00 MiB
                        time:   [158.18 µs 159.55 µs 161.20 µs]
                        thrpt:  [24.232 GiB/s 24.483 GiB/s 24.696 GiB/s]
                 change:
                        time:   [-91.411% -91.083% -90.750%] (p = 0.00 < 0.05)
                        thrpt:  [+981.14% +1021.5% +1064.3%]
                        Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
  2 (2.00%) high mild
  8 (8.00%) high severe
Benchmarking service_memory_read_full/16.0 MiB: Warming up for 3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase target time to 5.1s, enable flat sampling, or reduce sample count to 60.
Benchmarking service_memory_read_full/16.0 MiB: Collecting 100 samples in
service_memory_read_full/16.0 MiB
                        time:   [650.50 µs 665.93 µs 685.52 µs]
                        thrpt:  [22.793 GiB/s 23.463 GiB/s 24.020 GiB/s]
                 change:
                        time:   [-86.606% -85.507% -84.403%] (p = 0.00 < 0.05)
                        thrpt:  [+541.17% +589.98% +646.60%]
                        Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
  6 (6.00%) high mild
  7 (7.00%) high severe

Benchmarking service_memory_read_part/4.00 KiB: Collecting 100 samples in
service_memory_read_part/4.00 KiB
                        time:   [1.5394 µs 1.5486 µs 1.5601 µs]
                        thrpt:  [2.4452 GiB/s 2.4633 GiB/s 2.4780 GiB/s]
                 change:
                        time:   [-20.101% -17.674% -15.294%] (p = 0.00 < 0.05)
                        thrpt:  [+18.056% +21.469% +25.158%]
                        Performance has improved.
Found 10 outliers among 100 measurements (10.00%)
  3 (3.00%) high mild
  7 (7.00%) high severe
Benchmarking service_memory_read_part/256 KiB: Collecting 100 samples in 
service_memory_read_part/256 KiB
                        time:   [7.7092 µs 7.7592 µs 7.8239 µs]
                        thrpt:  [31.205 GiB/s 31.465 GiB/s 31.669 GiB/s]
                 change:
                        time:   [-86.704% -86.378% -86.029%] (p = 0.00 < 0.05)
                        thrpt:  [+615.76% +634.12% +652.12%]
                        Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
  3 (3.00%) high mild
  10 (10.00%) high severe
Benchmarking service_memory_read_part/4.00 MiB: Collecting 100 samples in
service_memory_read_part/4.00 MiB
                        time:   [226.75 µs 231.38 µs 236.93 µs]
                        thrpt:  [16.487 GiB/s 16.883 GiB/s 17.227 GiB/s]
                 change:
                        time:   [-86.637% -86.288% -85.918%] (p = 0.00 < 0.05)
                        thrpt:  [+610.13% +629.31% +648.33%]
                        Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
  5 (5.00%) high mild
  10 (10.00%) high severe
Benchmarking service_memory_read_part/16.0 MiB: Collecting 100 samples in
service_memory_read_part/16.0 MiB
                        time:   [959.30 µs 968.46 µs 978.50 µs]
                        thrpt:  [15.968 GiB/s 16.134 GiB/s 16.288 GiB/s]
                 change:
                        time:   [-91.789% -91.596% -91.368%] (p = 0.00 < 0.05)
                        thrpt:  [+1058.4% +1089.9% +1117.9%]
                        Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
  3 (3.00%) high mild
  8 (8.00%) high severe

Benchmarking service_memory_read_parallel/1x4.00 KiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/1x4.00 KiB: Collecting 100 samp
service_memory_read_parallel/1x4.00 KiB
                        time:   [1.6407 µs 1.6500 µs 1.6626 µs]
                        thrpt:  [2.2945 GiB/s 2.3119 GiB/s 2.3251 GiB/s]
                 change:
                        time:   [-29.670% -27.428% -25.149%] (p = 0.00 < 0.05)
                        thrpt:  [+33.598% +37.794% +42.186%]
                        Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
  4 (4.00%) high mild
  11 (11.00%) high severe
Benchmarking service_memory_read_parallel/2x4.00 KiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/2x4.00 KiB: Collecting 100 samp
service_memory_read_parallel/2x4.00 KiB
                        time:   [3.2478 µs 3.3074 µs 3.3796 µs]
                        thrpt:  [2.2575 GiB/s 2.3068 GiB/s 2.3491 GiB/s]
                 change:
                        time:   [-27.922% -26.191% -24.276%] (p = 0.00 < 0.05)
                        thrpt:  [+32.059% +35.486% +38.738%]
                        Performance has improved.
Found 15 outliers among 100 measurements (15.00%)
  4 (4.00%) high mild
  11 (11.00%) high severe
Benchmarking service_memory_read_parallel/4x4.00 KiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/4x4.00 KiB: Collecting 100 samp
service_memory_read_parallel/4x4.00 KiB
                        time:   [6.5296 µs 6.6643 µs 6.8432 µs]
                        thrpt:  [2.2298 GiB/s 2.2896 GiB/s 2.3369 GiB/s]
                 change:
                        time:   [-24.709% -22.859% -20.803%] (p = 0.00 < 0.05)
                        thrpt:  [+26.268% +29.633% +32.818%]
                        Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
  4 (4.00%) high mild
  13 (13.00%) high severe
Benchmarking service_memory_read_parallel/8x4.00 KiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/8x4.00 KiB: Collecting 100 samp
service_memory_read_parallel/8x4.00 KiB
                        time:   [12.832 µs 12.893 µs 12.969 µs]
                        thrpt:  [2.3531 GiB/s 2.3670 GiB/s 2.3782 GiB/s]
                 change:
                        time:   [-29.853% -27.735% -25.694%] (p = 0.00 < 0.05)
                        thrpt:  [+34.579% +38.380% +42.557%]
                        Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
  2 (2.00%) high mild
  11 (11.00%) high severe
Benchmarking service_memory_read_parallel/16x4.00 KiB: Warming up for 3.0
Benchmarking service_memory_read_parallel/16x4.00 KiB: Collecting 100 sam
service_memory_read_parallel/16x4.00 KiB
                        time:   [25.694 µs 25.898 µs 26.166 µs]
                        thrpt:  [2.3326 GiB/s 2.3567 GiB/s 2.3754 GiB/s]
                 change:
                        time:   [-37.503% -35.396% -33.119%] (p = 0.00 < 0.05)
                        thrpt:  [+49.520% +54.789% +60.008%]
                        Performance has improved.
Found 17 outliers among 100 measurements (17.00%)
  5 (5.00%) high mild
  12 (12.00%) high severe
Benchmarking service_memory_read_parallel/1x256 KiB: Warming up for 3.000
Benchmarking service_memory_read_parallel/1x256 KiB: Collecting 100 sampl
service_memory_read_parallel/1x256 KiB
                        time:   [20.712 µs 20.989 µs 21.365 µs]
                        thrpt:  [11.427 GiB/s 11.632 GiB/s 11.787 GiB/s]
                 change:
                        time:   [-79.918% -79.059% -78.186%] (p = 0.00 < 0.05)
                        thrpt:  [+358.42% +377.54% +397.95%]
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  3 (3.00%) high mild
  6 (6.00%) high severe
Benchmarking service_memory_read_parallel/2x256 KiB: Warming up for 3.000
Benchmarking service_memory_read_parallel/2x256 KiB: Collecting 100 sampl
service_memory_read_parallel/2x256 KiB
                        time:   [41.371 µs 41.728 µs 42.146 µs]
                        thrpt:  [11.585 GiB/s 11.701 GiB/s 11.802 GiB/s]
                 change:
                        time:   [-76.484% -75.755% -74.992%] (p = 0.00 < 0.05)
                        thrpt:  [+299.87% +312.46% +325.25%]
                        Performance has improved.
Found 16 outliers among 100 measurements (16.00%)
  7 (7.00%) high mild
  9 (9.00%) high severe
Benchmarking service_memory_read_parallel/4x256 KiB: Warming up for 3.000
Benchmarking service_memory_read_parallel/4x256 KiB: Collecting 100 sampl
service_memory_read_parallel/4x256 KiB
                        time:   [85.950 µs 87.812 µs 89.864 µs]
                        thrpt:  [10.867 GiB/s 11.121 GiB/s 11.362 GiB/s]
                 change:
                        time:   [-76.704% -76.022% -75.324%] (p = 0.00 < 0.05)
                        thrpt:  [+305.25% +317.05% +329.27%]
                        Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
  6 (6.00%) high mild
  5 (5.00%) high severe
Benchmarking service_memory_read_parallel/8x256 KiB: Warming up for 3.000
Benchmarking service_memory_read_parallel/8x256 KiB: Collecting 100 sampl
service_memory_read_parallel/8x256 KiB
                        time:   [166.18 µs 167.82 µs 169.67 µs]
                        thrpt:  [11.512 GiB/s 11.638 GiB/s 11.753 GiB/s]
                 change:
                        time:   [-78.378% -77.656% -76.908%] (p = 0.00 < 0.05)
                        thrpt:  [+333.05% +347.56% +362.50%]
                        Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
  4 (4.00%) high mild
  9 (9.00%) high severe
Benchmarking service_memory_read_parallel/16x256 KiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/16x256 KiB: Collecting 100 samp
service_memory_read_parallel/16x256 KiB
                        time:   [327.80 µs 330.28 µs 333.21 µs]
                        thrpt:  [11.723 GiB/s 11.827 GiB/s 11.917 GiB/s]
                 change:
                        time:   [-77.663% -77.111% -76.590%] (p = 0.00 < 0.05)
                        thrpt:  [+327.17% +336.88% +347.69%]
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  3 (3.00%) high mild
  6 (6.00%) high severe
Benchmarking service_memory_read_parallel/1x4.00 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/1x4.00 MiB: Collecting 100 samp
service_memory_read_parallel/1x4.00 MiB
                        time:   [446.93 µs 451.46 µs 457.05 µs]
                        thrpt:  [8.5467 GiB/s 8.6525 GiB/s 8.7402 GiB/s]
                 change:
                        time:   [-77.348% -76.596% -75.837%] (p = 0.00 < 0.05)
                        thrpt:  [+313.86% +327.28% +341.46%]
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  2 (2.00%) high mild
  7 (7.00%) high severe
Benchmarking service_memory_read_parallel/2x4.00 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/2x4.00 MiB: Collecting 100 samp
service_memory_read_parallel/2x4.00 MiB
                        time:   [898.27 µs 913.46 µs 934.51 µs]
                        thrpt:  [8.3600 GiB/s 8.5527 GiB/s 8.6973 GiB/s]
                 change:
                        time:   [-76.592% -75.751% -74.853%] (p = 0.00 < 0.05)
                        thrpt:  [+297.66% +312.40% +327.20%]
                        Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
  4 (4.00%) high mild
  8 (8.00%) high severe
Benchmarking service_memory_read_parallel/4x4.00 MiB: Warming up for 3.0000 s
Warning: Unable to complete 100 samples in 5.0s. You may wish to increase target time to 9.9s, enable flat sampling, or reduce sample count to 40.
Benchmarking service_memory_read_parallel/4x4.00 MiB: Collecting 100 samp
service_memory_read_parallel/4x4.00 MiB
                        time:   [1.7959 ms 1.8197 ms 1.8527 ms]
                        thrpt:  [8.4336 GiB/s 8.5868 GiB/s 8.7002 GiB/s]
                 change:
                        time:   [-79.570% -77.879% -76.200%] (p = 0.00 < 0.05)
                        thrpt:  [+320.17% +352.06% +389.48%]
                        Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
  4 (4.00%) high mild
  8 (8.00%) high severe
Benchmarking service_memory_read_parallel/8x4.00 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/8x4.00 MiB: Collecting 100 samp
service_memory_read_parallel/8x4.00 MiB
                        time:   [3.5764 ms 3.6201 ms 3.6749 ms]
                        thrpt:  [8.5036 GiB/s 8.6323 GiB/s 8.7379 GiB/s]
                 change:
                        time:   [-80.407% -79.456% -78.470%] (p = 0.00 < 0.05)
                        thrpt:  [+364.48% +386.76% +410.39%]
                        Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
  1 (1.00%) high mild
  3 (3.00%) high severe
Benchmarking service_memory_read_parallel/16x4.00 MiB: Warming up for 3.0
Benchmarking service_memory_read_parallel/16x4.00 MiB: Collecting 100 sam
service_memory_read_parallel/16x4.00 MiB
                        time:   [7.0765 ms 7.1492 ms 7.2442 ms]
                        thrpt:  [8.6276 GiB/s 8.7422 GiB/s 8.8320 GiB/s]
                 change:
                        time:   [-76.822% -76.508% -76.163%] (p = 0.00 < 0.05)
                        thrpt:  [+319.52% +325.68% +331.44%]
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  3 (3.00%) high mild
  2 (2.00%) high severe
Benchmarking service_memory_read_parallel/1x16.0 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/1x16.0 MiB: Collecting 100 samp
service_memory_read_parallel/1x16.0 MiB
                        time:   [2.5800 ms 2.6089 ms 2.6414 ms]
                        thrpt:  [5.9153 GiB/s 5.9891 GiB/s 6.0562 GiB/s]
                 change:
                        time:   [-90.838% -90.254% -89.645%] (p = 0.00 < 0.05)
                        thrpt:  [+865.76% +926.11% +991.45%]
                        Performance has improved.
Found 14 outliers among 100 measurements (14.00%)
  7 (7.00%) high mild
  7 (7.00%) high severe
Benchmarking service_memory_read_parallel/2x16.0 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/2x16.0 MiB: Collecting 100 samp
service_memory_read_parallel/2x16.0 MiB
                        time:   [4.8794 ms 4.9188 ms 4.9698 ms]
                        thrpt:  [6.2879 GiB/s 6.3532 GiB/s 6.4045 GiB/s]
                 change:
                        time:   [-90.667% -90.224% -89.800%] (p = 0.00 < 0.05)
                        thrpt:  [+880.41% +922.94% +971.49%]
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  5 (5.00%) high mild
  4 (4.00%) high severe
Benchmarking service_memory_read_parallel/4x16.0 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/4x16.0 MiB: Collecting 100 samp
service_memory_read_parallel/4x16.0 MiB
                        time:   [9.9120 ms 10.005 ms 10.118 ms]
                        thrpt:  [6.1770 GiB/s 6.2471 GiB/s 6.3055 GiB/s]
                 change:
                        time:   [-90.081% -89.692% -89.311%] (p = 0.00 < 0.05)
                        thrpt:  [+835.58% +870.10% +908.15%]
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  2 (2.00%) high mild
  3 (3.00%) high severe
Benchmarking service_memory_read_parallel/8x16.0 MiB: Warming up for 3.00
Benchmarking service_memory_read_parallel/8x16.0 MiB: Collecting 100 samp
service_memory_read_parallel/8x16.0 MiB
                        time:   [19.784 ms 20.026 ms 20.307 ms]
                        thrpt:  [6.1555 GiB/s 6.2420 GiB/s 6.3182 GiB/s]
                 change:
                        time:   [-88.641% -88.478% -88.309%] (p = 0.00 < 0.05)
                        thrpt:  [+755.33% +767.88% +780.37%]
                        Performance has improved.
Found 8 outliers among 100 measurements (8.00%)
  3 (3.00%) high mild
  5 (5.00%) high severe
Benchmarking service_memory_read_parallel/16x16.0 MiB: Warming up for 3.0
Benchmarking service_memory_read_parallel/16x16.0 MiB: Collecting 100 sam
service_memory_read_parallel/16x16.0 MiB
                        time:   [41.819 ms 42.512 ms 43.370 ms]
                        thrpt:  [5.7643 GiB/s 5.8807 GiB/s 5.9782 GiB/s]
                 change:
                        time:   [-91.795% -91.354% -90.887%] (p = 0.00 < 0.05)
                        thrpt:  [+997.29% +1056.6% +1118.8%]
                        Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
  3 (3.00%) high mild
  8 (8.00%) high severe

fs not set, ignore
s3 not set, ignore
Benchmarking service_memory_write_once/4.00 KiB: Collecting 100 samples i
service_memory_write_once/4.00 KiB
                        time:   [1.1547 µs 1.1624 µs 1.1718 µs]
                        thrpt:  [3.2555 GiB/s 3.2817 GiB/s 3.3035 GiB/s]
                 change:
                        time:   [-34.430% -31.696% -28.903%] (p = 0.00 < 0.05)
                        thrpt:  [+40.652% +46.405% +52.508%]
                        Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
  3 (3.00%) high mild
  8 (8.00%) high severe
Benchmarking service_memory_write_once/256 KiB: Collecting 100 samples in
service_memory_write_once/256 KiB
                        time:   [1.1560 µs 1.1631 µs 1.1717 µs]
                        thrpt:  [208.37 GiB/s 209.90 GiB/s 211.20 GiB/s]
                 change:
                        time:   [-95.660% -95.526% -95.394%] (p = 0.00 < 0.05)
                        thrpt:  [+2070.9% +2134.9% +2204.1%]
                        Performance has improved.
Found 13 outliers among 100 measurements (13.00%)
  4 (4.00%) high mild
  9 (9.00%) high severe
Benchmarking service_memory_write_once/4.00 MiB: Collecting 100 samples i
service_memory_write_once/4.00 MiB
                        time:   [1.2230 µs 1.2464 µs 1.2742 µs]
                        thrpt:  [3065.7 GiB/s 3134.0 GiB/s 3193.9 GiB/s]
                 change:
                        time:   [-99.859% -99.847% -99.835%] (p = 0.00 < 0.05)
                        thrpt:  [+60468% +65311% +70794%]
                        Performance has improved.
Found 11 outliers among 100 measurements (11.00%)
  10 (10.00%) high mild
  1 (1.00%) high severe
Benchmarking service_memory_write_once/16.0 MiB: Collecting 100 samples i
service_memory_write_once/16.0 MiB
                        time:   [1.1572 µs 1.1659 µs 1.1765 µs]
                        thrpt:  [ 13281 GiB/s  13402 GiB/s  13502 GiB/s]
                 change:
                        time:   [-99.958% -99.957% -99.956%] (p = 0.00 < 0.05)
                        thrpt:  [+227600% +232800% +238102%]
                        Performance has improved.
Found 12 outliers among 100 measurements (12.00%)
  3 (3.00%) high mild
  9 (9.00%) high severe

@PsiACE PsiACE deleted the typed-memory-kv branch May 8, 2023 07:28
suyanhanx pushed a commit to suyanhanx/opendal that referenced this pull request May 8, 2023
* feat(services/memory): migrate service memory

Signed-off-by: Chojan Shang <psiace@apache.org>

* docs(typed_kv): update capabilities

Signed-off-by: Chojan Shang <psiace@apache.org>

---------

Signed-off-by: Chojan Shang <psiace@apache.org>
@Xuanwo Xuanwo mentioned this pull request May 9, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Tracking issues of Typed KV Adapter
2 participants