Files
rippled/.github/scripts/telemetry/check_bucket_parity.py
Pratik Mankawde 9b1cd87d2e docs(telemetry): remove pre-squash references from the gap-fill comments
These comments dated themselves against this branch or against an earlier
revision of the same change, neither of which survives a squash merge.

- 'as of this branch' in the pricing-case doc and the pass-through static_assert
  becomes a statement about what the constants currently produce.
- 'Extracted from processGetObjectByHash()' and 'Split from start()' describe
  edits internal to this change; both now say why the method stands alone.
- Recording.h: the mock-abstract mismatch is a standing consequence of a member
  set that differs between builds, not something that 'has previously' happened.
- MetricsRegistry.cpp: describe the loops.txt entry as recording two cycles
  rather than as what ordering.txt 'previously had'.
- InboundLedger.h: the acquire span is the only signal for back-fill cost; it
  did not 'previously emit' nothing.
- check_bucket_parity.py: replace the eleven-phase drift story with the reason
  the check exists, and point the failure message at HistogramBuckets.h and the
  collector config instead of OpenTelemetryPlan/, which does not reach develop.

Comments and one error message only, no behaviour change.
2026-09-02 19:47:35 +01:00

131 lines
4.9 KiB
Python
Executable File

#!/usr/bin/env python3
"""Assert the C++ millisecond ladder agrees with the collector's spanmetrics ladder.
The two are specified to match so a span-derived latency panel and a native
histogram panel can be read on the same scale. Nothing else couples them, so
extending one ladder alone -- sub-millisecond edges below 1ms, second-scale
edges up to 30s -- silently leaves the other short. That failure is quiet:
Prometheus returns the second-highest edge for a quantile landing in the
`+Inf` bucket, so every quantile above a too-low ceiling reads back as a flat
number that looks like a measurement rather than an error. This check is what
makes the drift loud.
The rule is containment, not equality:
* every representable collector edge MUST appear in the C++ ladder, so the
shared range reads identically;
* the C++ ladder MAY carry extra edges ABOVE the collector's highest edge,
because jobs outlive spans -- the updatepaths job type was measured
averaging ~60s, which no span approaches. Demanding equality would force a
ceiling that censors it, recreating the failure this guards against;
* collector edges below 1ms are expected to be ABSENT rather than missing:
beast::insight::Event rounds every duration up to a whole millisecond
before it reaches the histogram, so those edges could never collect a
sample.
Exit 0 when the ladders agree, 1 with a diff when they do not.
"""
import re
import sys
from pathlib import Path
HEADER = Path("include/xrpl/telemetry/HistogramBuckets.h")
COLLECTOR = Path("docker/telemetry/otel-collector-config.yaml")
# beast::insight::Event applies ceil<milliseconds>, so anything below 1ms
# collapses onto the 1ms edge.
REPRESENTABLE_FLOOR_MS = 1.0
UNIT_TO_MS = {"ms": 1.0, "s": 1000.0}
def collector_edges_ms():
"""Parse the spanmetrics bucket list, normalising each edge to milliseconds."""
text = COLLECTOR.read_text()
match = re.search(r"buckets:\s*\[(.*?)\]", text, re.S)
if not match:
sys.exit(f"{COLLECTOR}: no 'buckets:' list found")
edges = []
for raw in match.group(1).split(","):
token = raw.strip()
if not token:
continue
parsed = re.fullmatch(r"([0-9.]+)(ms|s)", token)
if not parsed:
sys.exit(f"{COLLECTOR}: cannot parse bucket edge {token!r}")
edges.append(float(parsed.group(1)) * UNIT_TO_MS[parsed.group(2)])
return edges
def cpp_edges_ms():
"""Parse kMillisecondBuckets out of the header that owns every ladder."""
text = HEADER.read_text()
match = re.search(r"kMillisecondBuckets\{(.*?)\};", text, re.S)
if not match:
sys.exit(f"{HEADER}: kMillisecondBuckets not found")
return [
float(token.strip().replace("'", ""))
for token in match.group(1).split(",")
if token.strip()
]
def main():
collector = collector_edges_ms()
cpp = cpp_edges_ms()
required = [edge for edge in collector if edge >= REPRESENTABLE_FLOOR_MS]
if not required:
sys.exit(f"{COLLECTOR}: no edges at or above {REPRESENTABLE_FLOOR_MS} ms")
collector_top = max(required)
missing = [edge for edge in required if edge not in cpp]
# An extra C++ edge inside the collector's range means the two scales
# disagree where they overlap. Above the collector's top it is a deliberate
# extension.
inside_range = [e for e in cpp if e not in required and e < collector_top]
if not missing and not inside_range:
extensions = [e for e in cpp if e > collector_top]
summary = f"OK: all {len(required)} representable collector edges present"
if extensions:
pretty = ", ".join(f"{e:g}" for e in extensions)
summary += (
f"; {len(extensions)} extension edge(s) above "
f"{collector_top:g} ms: [{pretty}]"
)
print(summary)
return 0
print("Bucket ladder parity violated.", file=sys.stderr)
print(
f" collector (>= {REPRESENTABLE_FLOOR_MS:g} ms): "
f"{[f'{e:g}' for e in required]}",
file=sys.stderr,
)
print(
f" HistogramBuckets.h : {[f'{e:g}' for e in cpp]}", file=sys.stderr
)
for edge in missing:
print(f" MISSING from the C++ ladder: {edge:g} ms", file=sys.stderr)
for edge in inside_range:
print(
f" C++ edge {edge:g} ms lies inside the collector's range but is not "
"a collector edge -- add it to the collector or drop it here",
file=sys.stderr,
)
print(
"\nThe two ladders must agree over their shared range. Extra C++ edges are\n"
"permitted only ABOVE the collector's highest edge. To re-price the shared\n"
f"range, edit the ladder in {HEADER} and the\n"
f"spanmetrics 'buckets:' list in {COLLECTOR}\n"
"in the same change, so both sides stay in step.",
file=sys.stderr,
)
return 1
if __name__ == "__main__":
sys.exit(main())