go memorycache v1.1.2 update: 使用四叉堆替换二叉堆

[Nazz]

GitHub

四叉堆高度更低, 对 CPU 缓存更友好(Down 方法的 4 个比较操作有 3 个在相邻的同一层), 每个 Set 操作有几十纳秒的提升.

benchmark

从压测结果看, MemoryCache 的 Get 性能略高于 Ristretto, Set 性能远高于它. https://github.com/lxzan/memorycache/blob/main/benchmark/benchmark_test.go

go test -benchmem -run=^$ -bench . github.com/lxzan/memorycache/benchmark
goos: linux
goarch: amd64
pkg: github.com/lxzan/memorycache/benchmark
cpu: AMD Ryzen 5 PRO 4650G with Radeon Graphics
BenchmarkMemoryCache_Set-12     11499579               101.7 ns/op            16 B/op          0 allocs/op
BenchmarkMemoryCache_Get-12     26326636                45.97 ns/op            0 B/op          0 allocs/op
BenchmarkRistretto_Set-12       12341542               275.4 ns/op           119 B/op          2 allocs/op
BenchmarkRistretto_Get-12       22825676                50.12 ns/op           16 B/op          1 allocs/op
PASS
ok      github.com/lxzan/memorycache/benchmark  20.107s