mirror of
https://github.com/jmcorgan/fips.git
synced 2026-07-22 07:48:26 +00:00
9e63b42bd9
Replace 4 near-identical per-harness Docker setups with unified shared infrastructure. Net result: -463 lines across 55 files, faster CI (8.5 min vs ~13.5 min), 14 scenarios (down from 21). Unified Docker image (testing/docker/): - Single Dockerfile (trixie-slim) with FIPS_TEST_MODE env var for mode dispatch: default, chaos, sidecar, tor-socks5, tor-directory - Single entrypoint.sh with conditional logic per mode - Replaces 5 Dockerfiles, 3 entrypoints, 4 resolv.conf copies Shared build and libraries (testing/scripts/, testing/lib/): - testing/scripts/build.sh: single build script with macOS zigbuild support, replaces 4 per-harness copies - testing/lib/derive_keys.py: shared key derivation module, replaces 3 copies of derive-keys.py - testing/lib/log_analysis.py: shared log analysis extracted from chaos sim/logs.py, with CLI interface and rekey cutover tracking - testing/lib/wait-converge.sh: shared convergence wait helpers (wait_for_links, wait_for_peers) using fipsctl JSON polling Scenario consolidation: - Remove 7 redundant scenarios: tcp-chain (subsumed by tcp-mesh), tcp-only (subsumed by tcp-mesh), chaos-10 (replaced by churn-mixed --nodes 10), churn-10/churn-20/churn-20-mixed (subsumed by parameterized churn-mixed), cost-mixed-7node (overlaps mixed-technology) - Add churn-mixed scenario with --nodes flag for scale testing - Reduce idle scenario durations: smoke-10 60s→30s, ethernet-only 90s→30s, cost-avoidance 120s→45s, depth-vs-cost 120s→45s, bottleneck-parent 120s→60s, mixed-technology 180s→90s CI updates: - ci-local.sh: unified image build, structured chaos suite entries with per-scenario flags, --skip-build for sidecar - ci.yml: shared binary install + image build step, updated scenario matrix, chaos_flags support for parameterized scenarios - Add tcp-mesh and congestion-stress to CI matrix - Static ping test uses active peer convergence detection instead of hardcoded 5s sleep Chaos infrastructure improvements (from discovery-rework branch): - Pre-built Docker image instead of per-service build at scale - --nodes flag in chaos.sh for runtime topology size override
86 lines
2.5 KiB
Python
86 lines
2.5 KiB
Python
"""Log collection and post-run analysis for chaos simulations.
|
|
|
|
Delegates core analysis to the shared testing.lib.log_analysis module.
|
|
Adds chaos-specific collection (Docker container logs, sim metadata).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import os
|
|
import subprocess
|
|
|
|
# Import shared analysis from testing/lib/
|
|
import sys
|
|
_TESTING_DIR = os.path.join(os.path.dirname(__file__), "..", "..")
|
|
if _TESTING_DIR not in sys.path:
|
|
sys.path.insert(0, _TESTING_DIR)
|
|
|
|
from lib.log_analysis import ( # noqa: E402
|
|
AnalysisResult,
|
|
analyze_logs,
|
|
strip_ansi,
|
|
)
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
# Re-export for existing callers
|
|
__all__ = ["AnalysisResult", "analyze_logs", "collect_logs", "write_sim_metadata"]
|
|
|
|
|
|
def collect_logs(container_names: list[str], output_dir: str) -> dict[str, str]:
|
|
"""Collect all output (stdout + stderr) from all containers."""
|
|
os.makedirs(output_dir, exist_ok=True)
|
|
logs = {}
|
|
|
|
for name in container_names:
|
|
try:
|
|
result = subprocess.run(
|
|
["docker", "logs", name],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=30,
|
|
)
|
|
raw = result.stdout + result.stderr
|
|
log_text = strip_ansi(raw)
|
|
logs[name] = log_text
|
|
|
|
path = os.path.join(output_dir, f"{name}.log")
|
|
with open(path, "w") as f:
|
|
f.write(log_text)
|
|
|
|
except (subprocess.TimeoutExpired, Exception) as e:
|
|
log.warning("Failed to collect logs from %s: %s", name, e)
|
|
logs[name] = ""
|
|
|
|
return logs
|
|
|
|
|
|
def write_sim_metadata(
|
|
output_dir: str,
|
|
scenario_name: str,
|
|
seed: int,
|
|
num_nodes: int,
|
|
num_edges: int,
|
|
duration_secs: int,
|
|
topology=None,
|
|
):
|
|
"""Write simulation metadata for reproducibility."""
|
|
path = os.path.join(output_dir, "metadata.txt")
|
|
with open(path, "w") as f:
|
|
f.write(f"scenario: {scenario_name}\n")
|
|
f.write(f"seed: {seed}\n")
|
|
f.write(f"nodes: {num_nodes}\n")
|
|
f.write(f"edges: {num_edges}\n")
|
|
f.write(f"duration_secs: {duration_secs}\n")
|
|
|
|
if topology:
|
|
f.write("\nadjacency:\n")
|
|
for nid in sorted(topology.nodes):
|
|
node = topology.nodes[nid]
|
|
peers = sorted(node.peers)
|
|
f.write(f" {nid} ({node.docker_ip}): {', '.join(peers)}\n")
|
|
f.write("\nedges:\n")
|
|
for a, b in sorted(topology.edges):
|
|
f.write(f" {a} -- {b}\n")
|