mirror of
https://github.com/jmcorgan/fips.git
synced 2026-08-09 16:24:45 +00:00
Johnathan Corgan
b3a1fb464f
Six-node depth-4 mesh with an induced upstream parent flap. Asserts a
trailing-window ceiling on per-node `stats.bloom.sent` and a sanity
floor on parent-switch count over a ~3-4 min observation window.
Guards against the regression class where a spanning-tree update that
changes only an internal path edge (no root or depth delta) fails to
be properly contained and instead propagates to leaves as a sustained
bloom-traffic oscillation, visible only at fleet scale and only after
several minutes of uptime.
Adds a new chaos primitive (`link_swap`) for deterministic asymmetric
link-cost flapping and a post-run assertion framework with two
checks:
- `bloom_send_rate.max_per_node`: trailing-window ceiling on the
`show_bloom` stats counter delta. Calibrated against the
post-mortem reproduction harness data (per-variant counter table
against pre-fix vs post-fix binaries).
- `min_parent_switches.min_total`: sanity guard against a
misconfigured harness where the flap inducer fires but the
topology never produces a real parent-switch event (e.g., wrong
root election from a different seed). Without this, the
bloom-rate assertion would trivially pass on any binary
including a regressed one.
The runner exits 3 on assertion failure (alongside 0 success and 2
panic-detected). Threshold derivation is documented in the scenario
README; the seed pin is also documented there since smallest-NodeAddr
root election is sensitive to the pubkey hash ordering.
Wired into ci-local.sh's chaos pool and the GitHub CI chaos matrix.
64 lines
1.6 KiB
Python
64 lines
1.6 KiB
Python
"""CLI entry point: python -m sim <scenario.yaml>"""
|
|
|
|
import argparse
|
|
import logging
|
|
import sys
|
|
|
|
from .runner import SimRunner
|
|
from .scenario import load_scenario
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(
|
|
prog="sim",
|
|
description="FIPS stochastic network simulation",
|
|
)
|
|
parser.add_argument("scenario", help="Path to scenario YAML file")
|
|
parser.add_argument(
|
|
"-v", "--verbose", action="store_true", help="Enable debug logging"
|
|
)
|
|
parser.add_argument(
|
|
"--seed", type=int, default=None,
|
|
help="Override scenario seed",
|
|
)
|
|
parser.add_argument(
|
|
"--duration", type=int, default=None,
|
|
help="Override scenario duration in seconds",
|
|
)
|
|
args = parser.parse_args()
|
|
|
|
level = logging.DEBUG if args.verbose else logging.INFO
|
|
logging.basicConfig(
|
|
level=level,
|
|
format="%(asctime)s %(levelname)-5s %(name)s: %(message)s",
|
|
datefmt="%H:%M:%S",
|
|
)
|
|
|
|
try:
|
|
scenario = load_scenario(args.scenario)
|
|
except (FileNotFoundError, ValueError) as e:
|
|
print(f"Error loading scenario: {e}", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
# Apply CLI overrides
|
|
if args.seed is not None:
|
|
scenario.seed = args.seed
|
|
if args.duration is not None:
|
|
if args.duration < 1:
|
|
print("Error: --duration must be >= 1", file=sys.stderr)
|
|
sys.exit(1)
|
|
scenario.duration_secs = args.duration
|
|
|
|
runner = SimRunner(scenario)
|
|
result = runner.run()
|
|
|
|
if result and result.panics:
|
|
sys.exit(2)
|
|
if runner.assertions_failed:
|
|
sys.exit(3)
|
|
sys.exit(0)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|