fix(probe,scripts): make speed-test sweeps work headless and tell the truth

Three bugs found running the owed throughput sweeps (all three conspired
to make yesterday's 'transport does 1G+' numbers fabrications):

- the probe never advertised VIDEO_CAP_PROBE_SEQ, so every host DECLINED
  its speed tests; the zeroed decline reply divided a settle-window
  sliver by 1 ms and printed plausible-looking garbage. Advertise the
  cap (the shared-core reassembler windows probe-space frames) and
  detect the all-zero decline explicitly.
- an idle virtual desktop publishes no frames on damage-driven capture
  (Windows IDD-push), so the pipeline build timed out before the burst
  could run. The probe now injects a ±2 px cursor wiggle over the wire
  during --speed-test warmup — injected host-side into the right
  session, works headless everywhere.
- throughput-sweep.py: tracing emits ANSI color into pipes, which broke
  the key=value parser (crash on the first point); strip it, guard
  half-parsed lines, and surface host declines as a flag.

Also logs the whole-run receive stage split (PUNKTFUNK_PERF) at stream
end — the probe is the measurement tool for the client-pump wall.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-14 19:07:57 +02:00
parent 85513d1697
commit f2fa7828d6
2 changed files with 64 additions and 4 deletions
+50 -4
View File
@@ -470,7 +470,10 @@ async fn session(args: Args) -> Result<()> {
video_caps: { video_caps: {
// Always ask for per-AU host timings (0xCF) — this is a measurement tool, and the // Always ask for per-AU host timings (0xCF) — this is a measurement tool, and the
// host/network split is exactly what it exists to report. Old hosts ignore the bit. // host/network split is exactly what it exists to report. Old hosts ignore the bit.
let mut caps = punktfunk_core::quic::VIDEO_CAP_HOST_TIMING; // PROBE_SEQ: the shared-core reassembler windows probe-space frames, so the probe
// qualifies for `--speed-test` bursts; without the bit the host declines them.
let mut caps = punktfunk_core::quic::VIDEO_CAP_HOST_TIMING
| punktfunk_core::quic::VIDEO_CAP_PROBE_SEQ;
if std::env::var_os("PUNKTFUNK_CLIENT_10BIT").is_some() { if std::env::var_os("PUNKTFUNK_CLIENT_10BIT").is_some() {
caps |= punktfunk_core::quic::VIDEO_CAP_10BIT; caps |= punktfunk_core::quic::VIDEO_CAP_10BIT;
} }
@@ -639,11 +642,28 @@ async fn session(args: Args) -> Result<()> {
} else { } else {
0 0
}; };
let conn2 = conn.clone();
tokio::spawn(async move { tokio::spawn(async move {
use std::sync::atomic::Ordering::Relaxed; use std::sync::atomic::Ordering::Relaxed;
tokio::time::sleep(std::time::Duration::from_secs(2)).await; // let the stream warm up // Warm up the stream — and generate desktop activity while doing so. Damage-driven
// Baseline the packet-level counters right before the burst (video is paused during it, // capture paths (Windows IDD-push, a static headless desktop anywhere) publish NO
// so the delta is pure probe traffic plus a sliver of resumed video in the settle). // frame until something composes, and the host's pipeline build waits for a first
// frame — so an idle virtual display would time the whole speed test out. A ±2 px
// cursor wiggle over the wire is injected host-side into the right session/desktop.
for i in 0..20u32 {
let mv = InputEvent {
kind: InputKind::MouseMove,
_pad: [0; 3],
code: 0,
x: if i % 2 == 0 { 2 } else { -2 },
y: 0,
flags: 0,
};
let _ = conn2.send_datagram(mv.encode().to_vec().into());
tokio::time::sleep(std::time::Duration::from_millis(100)).await;
}
// Baseline the packet-level counters right before the burst (video is paused during it,
// so the delta is pure probe traffic plus a sliver of resumed video in the settle).
let base_pkts = rxp.load(Relaxed); let base_pkts = rxp.load(Relaxed);
let base_bytes = rxb.load(Relaxed); let base_bytes = rxb.load(Relaxed);
tracing::info!(target_kbps, duration_ms, "requesting speed-test probe"); tracing::info!(target_kbps, duration_ms, "requesting speed-test probe");
@@ -668,6 +688,15 @@ async fn session(args: Args) -> Result<()> {
return; return;
} }
}; };
// A declined burst comes back all-zero (duration_ms = 0) — e.g. the host predates
// speed tests. Say so instead of dividing a settle-window sliver by 1 ms.
if res.duration_ms == 0 {
tracing::error!(
"SPEED TEST declined by host (all-zero ProbeResult) — host too old, or it \
rejected the request; check the host log"
);
return;
}
// The reliable result can beat the last UDP shards — let the tail arrive before reading. // The reliable result can beat the last UDP shards — let the tail arrive before reading.
// Keep this short: video resumes the instant the burst ends, so a long settle counts // Keep this short: video resumes the instant the burst ends, so a long settle counts
// resumed-video packets against the probe (inflating recv past the host's wire count). // resumed-video packets against the probe (inflating recv past the host's wire count).
@@ -1242,6 +1271,23 @@ async fn session(args: Args) -> Result<()> {
s.flush().ok(); s.flush().ok();
} }
// PUNKTFUNK_PERF: cumulative receive-path stage split for the whole run — where the
// receive core's time went (kernel drain vs AES-GCM open vs reassembly+FEC). This is
// the measurement tool's view of the client-pump wall the 2026-07-14 sweeps pinned.
if let Some(p) = session.take_pump_perf() {
let per_pkt = |ns: u64| ns.checked_div(p.packets).unwrap_or(0);
tracing::info!(
recv_ms = p.recv_ns / 1_000_000,
decrypt_ms = p.decrypt_ns / 1_000_000,
reasm_ms = p.reasm_ns / 1_000_000,
packets = p.packets,
pkts_per_batch = p.packets.checked_div(p.batches.max(1)).unwrap_or(0),
decrypt_ns_pkt = per_pkt(p.decrypt_ns),
reasm_ns_pkt = per_pkt(p.reasm_ns),
"receive stage split (whole run, PUNKTFUNK_PERF)"
);
}
latencies_us.sort_unstable(); latencies_us.sort_unstable();
let pct = |p: f64| -> u64 { let pct = |p: f64| -> u64 {
if latencies_us.is_empty() { if latencies_us.is_empty() {
+14
View File
@@ -78,6 +78,14 @@ SPEED_LINE = "SPEED TEST complete"
# ---- output parsing ------------------------------------------------------- # ---- output parsing -------------------------------------------------------
ANSI_RE = re.compile(r"\x1b\[[0-9;]*m")
def strip_ansi(text: str) -> str:
"""tracing emits ANSI color even into a pipe; strip it or `key=value` never matches."""
return ANSI_RE.sub("", text)
def _field(line: str, key: str) -> str | None: def _field(line: str, key: str) -> str | None:
"""Extract `key=value` or `key="value"` from a tracing log line (order-agnostic).""" """Extract `key=value` or `key="value"` from a tracing log line (order-agnostic)."""
m = re.search(rf'\b{re.escape(key)}=(?:"([^"]*)"|(\S+))', line) m = re.search(rf'\b{re.escape(key)}=(?:"([^"]*)"|(\S+))', line)
@@ -90,6 +98,7 @@ def parse_speed_line(text: str) -> dict | None:
"""Find the 'SPEED TEST complete' line in probe output and pull its fields. """Find the 'SPEED TEST complete' line in probe output and pull its fields.
Field names mirror clients/probe/src/main.rs:698-708 exactly.""" Field names mirror clients/probe/src/main.rs:698-708 exactly."""
text = strip_ansi(text)
line = next((ln for ln in text.splitlines() if SPEED_LINE in ln), None) line = next((ln for ln in text.splitlines() if SPEED_LINE in ln), None)
if line is None: if line is None:
return None return None
@@ -116,7 +125,10 @@ def parse_speed_line(text: str) -> dict | None:
def scan_warnings(text: str) -> list[str]: def scan_warnings(text: str) -> list[str]:
"""Surface client-side red flags that change interpretation of the numbers.""" """Surface client-side red flags that change interpretation of the numbers."""
text = strip_ansi(text)
flags = [] flags = []
if "SPEED TEST declined" in text:
flags.append("host declined the speed test (old host build?) — check the host log")
if "UDP socket buffer capped" in text: if "UDP socket buffer capped" in text:
flags.append("client SO_RCVBUF capped below target (raise kern.ipc.maxsockbuf)") flags.append("client SO_RCVBUF capped below target (raise kern.ipc.maxsockbuf)")
if "falling back to per-packet sends" in text or "USO unsupported" in text: if "falling back to per-packet sends" in text or "USO unsupported" in text:
@@ -314,6 +326,8 @@ def main() -> int:
print(f" -> {t} Mbps ...", end="", flush=True) print(f" -> {t} Mbps ...", end="", flush=True)
parsed, flags, raw = run_point(bin_path, host, t, args) parsed, flags, raw = run_point(bin_path, host, t, args)
all_flags.update(flags) all_flags.update(flags)
if parsed is not None and parsed.get("delivered_mbps") is None:
parsed = None # SPEED TEST line present but unparseable — treat as a failed point
if parsed is None: if parsed is None:
print(" FAIL") print(" FAIL")
# surface why, briefly # surface why, briefly