def _run(
self,
strategy: Strategy,
schedule: Schedule, # noqa: C901
experiment: Experiment,
journal: Journal,
configuration: Configuration,
secrets: Secrets,
settings: Settings,
event_registry: EventHandlerRegistry) -> None:
experiment["title"] = substitute(experiment["title"], configuration,
secrets)
logger.info("Running experiment: {t}".format(t=experiment["title"]))
started_at = time.time()
journal = journal or initialize_run_journal(experiment)
event_registry.started(experiment, journal)
control = Control()
activity_pool, rollback_pool = get_background_pools(experiment)
hypo_pool = get_hypothesis_pool()
continous_hypo_event = threading.Event()
dry = experiment.get("dry", False)
if dry:
logger.warning("Dry mode enabled")
initialize_global_controls(experiment, configuration, secrets,
settings)
initialize_controls(experiment, configuration, secrets)
logger.info("Steady-state strategy: {}".format(strategy.value))
rollback_strategy = settings.get("runtime",
{}).get("rollbacks", {}).get(
"strategy", "default")
logger.info("Rollbacks strategy: {}".format(rollback_strategy))
exit_gracefully_with_rollbacks = True
with_ssh = has_steady_state_hypothesis_with_probes(experiment)
if not with_ssh:
logger.info("No steady state hypothesis defined. That's ok, just "
"exploring.")
try:
try:
control.begin("experiment", experiment, experiment,
configuration, secrets)
state = object()
if with_ssh and should_run_before_method(strategy):
state = run_gate_hypothesis(experiment, journal,
configuration, secrets,
event_registry, dry)
if state is not None:
if with_ssh and should_run_during_method(strategy):
run_hypothesis_during_method(hypo_pool,
continous_hypo_event,
strategy, schedule,
experiment, journal,
configuration, secrets,
event_registry, dry)
state = run_method(strategy, activity_pool, experiment,
journal, configuration, secrets,
event_registry, dry)
continous_hypo_event.set()
if journal["status"] not in ["interrupted", "aborted"]:
if with_ssh and (state is not None) and \
should_run_after_method(strategy):
run_deviation_validation_hypothesis(
experiment, journal, configuration, secrets,
event_registry, dry)
except InterruptExecution as i:
journal["status"] = "interrupted"
logger.fatal(str(i))
event_registry.interrupted(experiment, journal)
except KeyboardInterrupt:
journal["status"] = "interrupted"
logger.warning("Received a termination signal (Ctrl-C)...")
event_registry.signal_exit()
except SystemExit as x:
journal["status"] = "interrupted"
logger.warning("Received the exit signal: {}".format(x.code))
exit_gracefully_with_rollbacks = x.code != 30
if not exit_gracefully_with_rollbacks:
logger.warning("Ignoring rollbacks as per signal")
event_registry.signal_exit()
finally:
hypo_pool.shutdown(wait=True)
# just in case a signal overrode everything else to tell us not to
# play them anyway (see the exit.py module)
if exit_gracefully_with_rollbacks:
run_rollback(rollback_strategy, rollback_pool, experiment,
journal, configuration, secrets, event_registry,
dry)
journal["end"] = datetime.utcnow().isoformat()
journal["duration"] = time.time() - started_at
# the spec only allows these statuses, so if it's anything else
# we override to "completed"
if journal["status"] not in ("completed", "failed", "aborted",
"interrupted"):
journal["status"] = "completed"
has_deviated = journal["deviated"]
status = "deviated" if has_deviated else journal["status"]
logger.info("Experiment ended with status: {s}".format(s=status))
if has_deviated:
logger.info(
"The steady-state has deviated, a weakness may have been "
"discovered")
control.with_state(journal)
try:
control.end("experiment", experiment, experiment,
configuration, secrets)
except ChaosException:
logger.debug("Failed to close controls", exc_info=True)
finally:
try:
cleanup_controls(experiment)
cleanup_global_controls()
finally:
event_registry.finish(journal)
return journal
def run_experiment(experiment: Experiment,
settings: Settings = None) -> Journal:
"""
Run the given `experiment` method step by step, in the following sequence:
steady probe, action, close probe.
Activities can be executed in background when they have the
`"background"` property set to `true`. In that case, the activity is run in
a thread. By the end of runs, those threads block until they are all
complete.
If the experiment has the `"dry"` property set to `False`, the experiment
runs without actually executing the activities.
NOTE: Tricky to make a decision whether we should rollback when exiting
abnormally (Ctrl-C, SIGTERM...). Afterall, there is a chance we actually
cannot afford to rollback properly. Better bailing to a conservative
approach. This means we swallow :exc:`KeyboardInterrupt` and
:exc:`SystemExit` and do not bubble it back up to the caller. We when were
interrupted, we set the `interrupted` flag of the result accordingly to
notify the caller this was indeed not terminated properly.
"""
logger.info("Running experiment: {t}".format(t=experiment["title"]))
dry = experiment.get("dry", False)
if dry:
logger.warning("Dry mode enabled")
started_at = time.time()
settings = settings if settings is not None else get_loaded_settings()
config = load_configuration(experiment.get("configuration", {}))
secrets = load_secrets(experiment.get("secrets", {}), config)
initialize_global_controls(experiment, config, secrets, settings)
initialize_controls(experiment, config, secrets)
activity_pool, rollback_pool = get_background_pools(experiment)
control = Control()
journal = initialize_run_journal(experiment)
try:
try:
control.begin("experiment", experiment, experiment, config,
secrets)
# this may fail the entire experiment right there if any of the
# probes fail or fall out of their tolerance zone
try:
state = run_steady_state_hypothesis(experiment,
config,
secrets,
dry=dry)
journal["steady_states"]["before"] = state
if state is not None and not state["steady_state_met"]:
p = state["probes"][-1]
raise ActivityFailed(
"Steady state probe '{p}' is not in the given "
"tolerance so failing this experiment".format(
p=p["activity"]["name"]))
except ActivityFailed as a:
journal["steady_states"]["before"] = state
journal["status"] = "failed"
logger.fatal(str(a))
else:
try:
journal["run"] = apply_activities(experiment, config,
secrets, activity_pool,
dry)
except Exception:
journal["status"] = "aborted"
logger.fatal(
"Experiment ran into an un expected fatal error, "
"aborting now.",
exc_info=True)
else:
try:
state = run_steady_state_hypothesis(experiment,
config,
secrets,
dry=dry)
journal["steady_states"]["after"] = state
if state is not None and not state["steady_state_met"]:
journal["deviated"] = True
p = state["probes"][-1]
raise ActivityFailed(
"Steady state probe '{p}' is not in the given "
"tolerance so failing this experiment".format(
p=p["activity"]["name"]))
except ActivityFailed as a:
journal["status"] = "failed"
logger.fatal(str(a))
except InterruptExecution as i:
journal["status"] = "interrupted"
logger.fatal(str(i))
except (KeyboardInterrupt, SystemExit):
journal["status"] = "interrupted"
logger.warn("Received an exit signal, "
"leaving without applying rollbacks.")
else:
journal["status"] = journal["status"] or "completed"
journal["rollbacks"] = apply_rollbacks(experiment, config, secrets,
rollback_pool, dry)
journal["end"] = datetime.utcnow().isoformat()
journal["duration"] = time.time() - started_at
has_deviated = journal["deviated"]
status = "deviated" if has_deviated else journal["status"]
logger.info("Experiment ended with status: {s}".format(s=status))
if has_deviated:
logger.info(
"The steady-state has deviated, a weakness may have been "
"discovered")
control.with_state(journal)
try:
control.end("experiment", experiment, experiment, config, secrets)
except ChaosException:
logger.debug("Failed to close controls", exc_info=True)
finally:
cleanup_controls(experiment)
cleanup_global_controls()
return journal