3afbfb42cf
Some checks failed
CI / test (push) Failing after 1m42s
Adds four Criterion.rs benchmark suites to measure hot-path performance
and demonstrate the impact of Sprints 1–3 optimizations:
- benches/protocol.rs — Command & StatusMessage serialize/deserialize
- benches/bandwidth.rs — BandwidthState atomics, budget, interval math
- benches/tcp_rx_scan.rs — memchr SIMD scan vs naive O(n) loop (55× faster
on 256KB buffers with status at end)
- benches/ecsrp5.rs — WCurve::new() heavy math vs cached LazyLock
(~123,000× faster access)
Also adds BENCHMARKS.md with usage instructions and example results.
Visibility changes (bench-only):
- scan_status_message is now pub (was #[cfg(test)] only)
- WCurve and WCURVE are now pub in ecsrp5.rs
dev-dependencies: criterion + pprof (optional flamegraph support)
101 lines
3.5 KiB
Rust
101 lines
3.5 KiB
Rust
use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion, Throughput};
|
|
use btest_rs::client::scan_status_message;
|
|
use btest_rs::protocol::STATUS_MSG_TYPE;
|
|
|
|
/// Naive O(n) byte-by-byte scan — the old implementation.
|
|
fn naive_scan(buf: &[u8]) -> Option<u8> {
|
|
const STATUS_MSG_SIZE: usize = 12;
|
|
if buf.len() < STATUS_MSG_SIZE {
|
|
return None;
|
|
}
|
|
for i in 0..=(buf.len() - STATUS_MSG_SIZE) {
|
|
if buf[i] == STATUS_MSG_TYPE && buf[i + 1] >= 0x80 {
|
|
return Some((buf[i + 1] & 0x7F).min(100));
|
|
}
|
|
}
|
|
None
|
|
}
|
|
|
|
fn make_buffer(size: usize, status_at: Option<usize>) -> Vec<u8> {
|
|
let mut buf = vec![0u8; size];
|
|
if let Some(pos) = status_at {
|
|
buf[pos] = STATUS_MSG_TYPE;
|
|
buf[pos + 1] = 0x80 | 50; // CPU = 50%
|
|
}
|
|
buf
|
|
}
|
|
|
|
fn bench_scan_all_zeros(c: &mut Criterion) {
|
|
let mut group = c.benchmark_group("tcp_rx_scan_all_zeros");
|
|
for size in [4096, 65536, 262144] {
|
|
let buf = make_buffer(size, None);
|
|
group.throughput(Throughput::Bytes(size as u64));
|
|
group.bench_with_input(BenchmarkId::new("naive", size), &buf, |b, buf| {
|
|
b.iter(|| black_box(naive_scan(black_box(buf))))
|
|
});
|
|
group.bench_with_input(BenchmarkId::new("memchr", size), &buf, |b, buf| {
|
|
b.iter(|| black_box(scan_status_message(black_box(&[]), black_box(buf))))
|
|
});
|
|
}
|
|
group.finish();
|
|
}
|
|
|
|
fn bench_scan_status_at_start(c: &mut Criterion) {
|
|
let mut group = c.benchmark_group("tcp_rx_scan_status_at_start");
|
|
for size in [4096, 65536, 262144] {
|
|
let buf = make_buffer(size, Some(0));
|
|
group.throughput(Throughput::Bytes(size as u64));
|
|
group.bench_with_input(BenchmarkId::new("naive", size), &buf, |b, buf| {
|
|
b.iter(|| black_box(naive_scan(black_box(buf))))
|
|
});
|
|
group.bench_with_input(BenchmarkId::new("memchr", size), &buf, |b, buf| {
|
|
b.iter(|| black_box(scan_status_message(black_box(&[]), black_box(buf))))
|
|
});
|
|
}
|
|
group.finish();
|
|
}
|
|
|
|
fn bench_scan_status_at_end(c: &mut Criterion) {
|
|
let mut group = c.benchmark_group("tcp_rx_scan_status_at_end");
|
|
for size in [4096, 65536, 262144] {
|
|
let buf = make_buffer(size, Some(size - 12));
|
|
group.throughput(Throughput::Bytes(size as u64));
|
|
group.bench_with_input(BenchmarkId::new("naive", size), &buf, |b, buf| {
|
|
b.iter(|| black_box(naive_scan(black_box(buf))))
|
|
});
|
|
group.bench_with_input(BenchmarkId::new("memchr", size), &buf, |b, buf| {
|
|
b.iter(|| black_box(scan_status_message(black_box(&[]), black_box(buf))))
|
|
});
|
|
}
|
|
group.finish();
|
|
}
|
|
|
|
fn bench_scan_split_message(c: &mut Criterion) {
|
|
// Simulate a status message split across two reads:
|
|
// carry has first 5 bytes, buf has remaining 7 bytes
|
|
let mut carry = vec![0u8; 5];
|
|
carry[0] = STATUS_MSG_TYPE;
|
|
carry[1] = 0x80 | 75;
|
|
let buf = vec![0u8; 7];
|
|
|
|
c.bench_function("scan_split_5_7", |b| {
|
|
b.iter(|| black_box(scan_status_message(black_box(&carry), black_box(&buf))))
|
|
});
|
|
|
|
// Split with 2 bytes in carry (status type + cpu byte), 10 in buf
|
|
let carry_2 = vec![STATUS_MSG_TYPE, 0x80 | 33];
|
|
let buf_10 = vec![0u8; 10];
|
|
c.bench_function("scan_split_2_10", |b| {
|
|
b.iter(|| black_box(scan_status_message(black_box(&carry_2), black_box(&buf_10))))
|
|
});
|
|
}
|
|
|
|
criterion_group!(
|
|
tcp_rx_scan_benches,
|
|
bench_scan_all_zeros,
|
|
bench_scan_status_at_start,
|
|
bench_scan_status_at_end,
|
|
bench_scan_split_message
|
|
);
|
|
criterion_main!(tcp_rx_scan_benches);
|