mirror of
https://github.com/jmcorgan/fips.git
synced 2026-07-30 19:46:15 +00:00
Johnathan Corgan
965de26239
A CI worker may preempt an in-flight ci-local.sh run (SIGTERM, then SIGKILL after a grace period) to restart on a newer commit. For that kill to be safe, the script must clean up after itself and never let a dying run collide with its restart. It previously had no signal handling, shared the default compose project name across runs, and tore down each suite only at the suite end. - Derive a per-run id (honoring FIPS_CI_RUN_ID, else short-sha+random) and namespace every docker resource to it: a fipsci_<run>_<suite> compose project per suite and per parallel chaos child, and per-run image tags (fips-test:<run>, fips-test-app:<run>) retagged to :latest only after both builds succeed so :latest never points at a half-built image. - Install a bounded, idempotent teardown trap on SIGTERM/SIGINT (+ EXIT): reap parallel chaos children, then force-remove this run's docker resources via the new ci-cleanup.sh, wrapped in timeout so a stuck down cannot wedge it. - Exit 143 (SIGTERM) / 130 (SIGINT), distinct from 0 (pass) / 1 (failed), so a preempting worker tells a cancelled run from a real failure. - Add ci-cleanup.sh (also ci-local.sh --reap): force-removes leftover CI resources by the com.corganlabs.fips-ci=1 label and the fipsci_ project prefix, robust to however a prior run died. - Label every per-suite docker resource so the label sweep reaps it after a SIGKILL regardless of network name: direct docker run/network resources, the sidecar compose services, and every per-suite compose network (acl-allowlist, boringtun, firewall, nat, static, both tor suites, and the chaos generator template). Parametrize the static/sidecar compose image refs so the per-run tags are honored. - Give each parallel chaos child a unique /24 from 10.30.x (a new --subnet override on the sim CLI, assigned per-child in ci-local.sh) so parallel children never collide on a shared docker subnet, and a chaos net can never span a fixed-subnet suite (sidecar/static in 172.20.x). 10.30.x sits outside docker's default-address-pool range, so an auto-assigned net cannot land on it either; node IPs derive from the subnet, so no scenario config changes.
92 lines
2.2 KiB
Python
92 lines
2.2 KiB
Python
"""Generate docker-compose.yml for a simulation topology."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
|
|
from jinja2 import Template
|
|
|
|
from .scenario import Scenario
|
|
from .topology import SimTopology
|
|
|
|
# Image name for the pre-built FIPS test image.
|
|
# The runner builds this once before starting containers.
|
|
FIPS_SIM_IMAGE = "fips-test:latest"
|
|
|
|
# Jinja2 template for the compose file.
|
|
# Uses a pre-built image instead of per-service build to support large topologies.
|
|
_COMPOSE_TEMPLATE = Template(
|
|
"""\
|
|
networks:
|
|
fips-net:
|
|
driver: bridge
|
|
labels:
|
|
- "com.corganlabs.fips-ci=1"
|
|
ipam:
|
|
config:
|
|
- subnet: {{ subnet }}
|
|
|
|
x-fips-common: &fips-common
|
|
image: {{ image }}
|
|
cap_add:
|
|
- NET_ADMIN
|
|
- NET_RAW
|
|
devices:
|
|
- /dev/net/tun:/dev/net/tun
|
|
sysctls:
|
|
- net.ipv6.conf.all.disable_ipv6=0
|
|
restart: "no"
|
|
env_file:
|
|
- ./npubs.env
|
|
environment:
|
|
- RUST_LOG={{ rust_log }}
|
|
- RUST_BACKTRACE=1
|
|
- FIPS_TEST_MODE=chaos
|
|
|
|
services:
|
|
{% for node in nodes %}
|
|
{{ node.node_id }}:
|
|
<<: *fips-common
|
|
container_name: fips-node-{{ node.node_id }}
|
|
hostname: {{ node.node_id }}
|
|
volumes:
|
|
- ./{{ node.node_id }}.yaml:/etc/fips/fips.yaml:ro
|
|
- {{ resolv_conf }}:/etc/resolv.conf:ro
|
|
networks:
|
|
fips-net:
|
|
ipv4_address: {{ node.docker_ip }}
|
|
{% endfor %}
|
|
"""
|
|
)
|
|
|
|
|
|
def generate_compose(
|
|
topology: SimTopology,
|
|
scenario: Scenario,
|
|
output_dir: str,
|
|
) -> str:
|
|
"""Render docker-compose.yml and write to output_dir. Returns the file path."""
|
|
os.makedirs(output_dir, exist_ok=True)
|
|
|
|
nodes = [topology.nodes[nid] for nid in sorted(topology.nodes)]
|
|
|
|
# Absolute path to the shared resolv.conf (bind-mounted into containers
|
|
# so Docker's runtime resolv.conf generation doesn't overwrite it).
|
|
resolv_conf = os.path.normpath(
|
|
os.path.join(os.path.dirname(__file__), "..", "..", "docker", "resolv.conf")
|
|
)
|
|
|
|
content = _COMPOSE_TEMPLATE.render(
|
|
subnet=scenario.topology.subnet,
|
|
rust_log=scenario.logging.rust_log,
|
|
image=FIPS_SIM_IMAGE,
|
|
nodes=nodes,
|
|
resolv_conf=resolv_conf,
|
|
)
|
|
|
|
path = os.path.join(output_dir, "docker-compose.yml")
|
|
with open(path, "w") as f:
|
|
f.write(content)
|
|
|
|
return path
|