petrbalvin
a9b8039ef7
Test / test (push) Successful in 2m4s
Release / gates (push) Successful in 2m5s
Release / build (amd64, freebsd) (push) Successful in 1m27s
Release / build (amd64, linux) (push) Successful in 1m22s
Release / build (amd64, netbsd) (push) Successful in 1m19s
Release / build (amd64, openbsd) (push) Successful in 1m20s
Release / build (arm64, darwin) (push) Successful in 1m21s
Release / build (arm64, freebsd) (push) Successful in 1m26s
Release / build (arm64, linux) (push) Successful in 1m25s
Release / build (arm64, netbsd) (push) Successful in 1m31s
Release / build (arm64, openbsd) (push) Successful in 1m27s
Release / build (loong64, linux) (push) Successful in 1m37s
Release / build (riscv64, linux) (push) Successful in 1m21s
Release / release (push) Successful in 40s
Assisted-by: GLM 5.3 Flash
32 lines
1.3 KiB
Markdown
32 lines
1.3 KiB
Markdown
# Measurement: the descriptor cache in internal/nfsfs
|
|
|
|
- Date: 2026-09-22
|
|
- Machine: AMD Ryzen AI Max+ Pro 395 (32 threads), idle
|
|
- Toolchain: go1.27.1, no build flags
|
|
- Command: `go test ./internal/nfsfs/ -run '^$' -bench=. -benchmem -count=5`
|
|
|
|
## Baseline
|
|
|
|
The commit b8758b7, the head of development before the descriptor cache: every
|
|
READ, WRITE and SYNC opened the registered path, verified it with a stat and
|
|
closed the descriptor again, per operation. The cache keeps idle descriptors of
|
|
regular files in a bounded LRU and revalidates the identity on every use, so the
|
|
measurements answer one question: what the open and close per operation cost.
|
|
|
|
## Result
|
|
|
|
Median of five runs, same session, same machine.
|
|
|
|
| Benchmark | Baseline | With cache | Change |
|
|
|---|---|---|---|
|
|
| `BenchmarkRead64K` | 10888 ns/op | 9047 ns/op | -16.9 % |
|
|
| `BenchmarkWrite64K` | 5881 ns/op | 5236 ns/op | -11.0 % |
|
|
| `BenchmarkGetattr` | 461.4 ns/op | 437.2 ns/op | -5.2 % |
|
|
| `BenchmarkLookup` | 1216 ns/op | 1134 ns/op | -6.7 % |
|
|
|
|
The two data operations are the ones the cache touches, and they gain 11 to 17
|
|
percent per operation. GETATTR and LOOKUP run the same code as before the cache
|
|
(they resolve paths through Lstat either way), so their shifts are code layout
|
|
noise of the same binary, not an effect to claim; both sit within the run to run
|
|
spread the five repetitions showed.
|