mirror of
https://github.com/jmcorgan/fips.git
synced 2026-07-30 19:46:15 +00:00
Johnathan Corgan
4f55a281ac
The simulation caught every exception a scenario raised, logged it, and exited 0, so a scenario that died during setup was recorded as a pass. Local CI discarded the exit code in any case: run_chaos ends in a call whose own last statement is an echo, so it returned 0 whatever the scenario did, and the parallel launcher's wait therefore always succeeded and always recorded a pass. Between them no chaos failure of any kind could turn a local run red, and none could since the script was written. Carry the abort out of the run and give it its own exit code, ordered ahead of the two content codes so a run that never produced a mesh cannot report that mesh's panic and assertion counts. Return the scenario's status from run_chaos so the launcher sees it. The documented exit codes were stale before this change and are rewritten in full, including that the argument parser rejects a malformed command line with the same code that reports panics. Expect scenarios that have been reporting green to start reporting red. In the last recorded local run twelve of the thirteen scenarios never got past starting their containers, and all thirteen were counted as passes; those that now execute have not run for months, and their assertions have never been evaluated against a mesh of their own.
77 lines
2.2 KiB
Python
77 lines
2.2 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",
|
|
)
|
|
parser.add_argument(
|
|
"--subnet", type=str, default=None,
|
|
help="Override topology subnet CIDR (e.g. 10.30.0.0/24); node IPs "
|
|
"derive from it. Used by CI to give each parallel run a "
|
|
"non-overlapping network.",
|
|
)
|
|
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
|
|
if args.subnet is not None:
|
|
scenario.topology.subnet = args.subnet
|
|
|
|
runner = SimRunner(scenario)
|
|
result = runner.run()
|
|
|
|
# Liveness before content. A simulation that raised on its way up, or part
|
|
# way through, has no panic count or assertion outcome worth reporting, and
|
|
# saying so is more useful than whatever partial content it did produce.
|
|
if runner.aborted:
|
|
sys.exit(4)
|
|
if result and result.panics:
|
|
sys.exit(2)
|
|
if runner.assertions_failed:
|
|
sys.exit(3)
|
|
sys.exit(0)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|