Files
conflict-set/README.md
Andrew Noyes d1dc1247e1
Some checks failed
Tests / Clang total: 1479, passed: 1479
Clang |Total|New|Outstanding|Fixed|Trend |:-:|:-:|:-:|:-:|:-: |0|0|0|0|:clap:
Tests / Debug total: 1477, passed: 1477
weaselab/conflict-set/pipeline/head There was a failure building this commit
Switch to new machine for benchmarks
2024-08-02 18:18:36 -07:00

60 lines
4.4 KiB
Markdown

A data structure for optimistic concurrency control on ranges of bitwise-lexicographically-ordered keys.
Intended as an alternative to FoundationDB's skip list.
Hardware for all benchmarks is an AMD Ryzen 9 7900 with (2x32GB) 5600MT/s CL28-34-34-89 1.35V RAM
# Microbenchmark
## Skip list
| ns/op | op/s | err% | ins/op | cyc/op | IPC | bra/op | miss% | total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
| 172.03 | 5,812,791.77 | 0.4% | 3,130.62 | 879.00 | 3.562 | 509.23 | 0.0% | 0.01 | `point reads`
| 167.44 | 5,972,130.71 | 0.2% | 3,065.14 | 862.27 | 3.555 | 494.30 | 0.0% | 0.01 | `prefix reads`
| 238.77 | 4,188,130.84 | 0.9% | 3,589.93 | 1,259.30 | 2.851 | 637.12 | 0.0% | 0.01 | `range reads`
| 424.01 | 2,358,426.70 | 0.2% | 5,620.05 | 2,242.35 | 2.506 | 854.80 | 1.7% | 0.01 | `point writes`
| 418.45 | 2,389,780.56 | 0.4% | 5,525.07 | 2,211.05 | 2.499 | 831.71 | 1.7% | 0.01 | `prefix writes`
| 254.87 | 3,923,568.88 | 2.6% | 3,187.01 | 1,366.50 | 2.332 | 529.11 | 2.7% | 0.02 | `range writes`
| 675.96 | 1,479,374.50 | 3.3% | 7,735.41 | 3,468.60 | 2.230 | 1,386.02 | 1.8% | 0.01 | `monotonic increasing point writes`
| 137,986.20 | 7,247.10 | 0.6% | 789,752.33 | 699,462.00 | 1.129 | 144,824.14 | 0.0% | 0.01 | `worst case for radix tree`
| 21.63 | 46,231,564.03 | 1.0% | 448.00 | 107.14 | 4.181 | 84.00 | 0.0% | 0.01 | `create and destroy`
## Radix tree (this implementation)
| ns/op | op/s | err% | ins/op | cyc/op | IPC | bra/op | miss% | total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
| 17.03 | 58,732,967.93 | 0.6% | 276.28 | 87.96 | 3.141 | 52.15 | 0.4% | 0.01 | `point reads`
| 19.52 | 51,239,158.04 | 0.3% | 367.16 | 101.50 | 3.617 | 61.92 | 0.3% | 0.01 | `prefix reads`
| 47.74 | 20,947,676.63 | 0.5% | 998.16 | 247.43 | 4.034 | 161.64 | 0.2% | 0.01 | `range reads`
| 23.14 | 43,207,824.89 | 0.4% | 408.18 | 121.64 | 3.356 | 70.20 | 0.3% | 0.01 | `point writes`
| 38.02 | 26,302,115.66 | 0.1% | 709.72 | 199.70 | 3.554 | 134.26 | 0.3% | 0.01 | `prefix writes`
| 44.28 | 22,583,559.17 | 0.9% | 825.19 | 233.10 | 3.540 | 141.48 | 0.2% | 0.01 | `range writes`
| 85.50 | 11,695,990.63 | 0.5% | 1,488.16 | 455.68 | 3.266 | 289.22 | 0.1% | 0.01 | `monotonic increasing point writes`
| 338,388.50 | 2,955.18 | 3.3% | 4,097,087.00 | 1,809,996.00 | 2.264 | 759,645.00 | 0.0% | 0.01 | `worst case for radix tree`
| 84.84 | 11,787,313.59 | 1.4% | 1,716.02 | 440.50 | 3.896 | 271.00 | 0.0% | 0.01 | `create and destroy`
# "Real data" test
Point queries only, best of three runs. Gc ratio is the ratio of time spent doing garbage collection to time spent adding writes or doing garbage collection. Lower is better.
## skip list
```
Check: 4.47891 seconds, 364.05 MB/s, Add: 4.55599 seconds, 123.058 MB/s, Gc ratio: 37.1145%
```
## radix tree
```
Check: 1.05813 seconds, 1540.97 MB/s, Add: 1.32071 seconds, 424.508 MB/s, Gc ratio: 42.2067%
```
## hash table
(The hash table implementation doesn't work on range queries, and its purpose is to provide an idea of how fast point queries can be)
```
Check: 0.804094 seconds, 2027.81 MB/s, Add: 0.652952 seconds, 858.645 MB/s, Gc ratio: 35.3885%
```