huntedbytheirs
180c1107b6
Establish the repository layout per Vox guidelines (layouts/C.md, building/C.md): Autotools build (GCC-only, C23), five compatibility profiles (--enable-onlyposix/--enable-muslmimic/--enable-muslext/ --enable-spoof, default vlibc), alongside/overwrite install methods, vlibc-gcc/vlibc-clang drivers, static-linking requirement (except spoof), benchmark harness, and tooling (.clang-format/.clang-tidy/ .clangd + compile_commands.json).
34 lines
1.0 KiB
Markdown
34 lines
1.0 KiB
Markdown
# Benchmarking
|
|
|
|
Every vlibc component is benchmarked against the software it replaces, per
|
|
`musts/BENCHMARKING.md`. A component that is slower or worse at its task than
|
|
the software it replaces is considered failing.
|
|
|
|
## Layout
|
|
|
|
- Each benchmark harness is a standalone C program in this directory, named
|
|
`bench_<component>.c`.
|
|
- `bench_vlibc.c` is the skeleton that per-component benchmarks build on.
|
|
|
|
## Running
|
|
|
|
```sh
|
|
./autogen.sh # configure (default: link against vlibc)
|
|
make bench # build and run the harnesses
|
|
|
|
# Reference comparison against the libc vlibc replaces:
|
|
./autogen.sh --with-libc=glibc
|
|
make bench
|
|
|
|
# musl reference (requires musl-gcc):
|
|
./autogen.sh --with-libc=musl
|
|
make bench
|
|
```
|
|
|
|
## Adding a benchmark
|
|
|
|
1. Add `bench_<component>.c` here and list it in `benchmarks/Makefile.am`.
|
|
2. Measure the component against the equivalent glibc (and musl) call.
|
|
3. Report wall-clock time, throughput, and any binary-size difference.
|
|
4. If vlibc is slower, the benchmark fails — fix the implementation.
|