def handle_distributed_coach_orchestrator(graph_manager, args):
ckpt_inside_container = "/checkpoint"
rollout_command = ['python3', 'rl_coach/coach.py', '--distributed_coach_run_type', str(RunType.ROLLOUT_WORKER)] + sys.argv[1:]
trainer_command = ['python3', 'rl_coach/coach.py', '--distributed_coach_run_type', str(RunType.TRAINER)] + sys.argv[1:]
if '--experiment_name' not in rollout_command:
rollout_command = rollout_command + ['--experiment_name', args.experiment_name]
if '--experiment_name' not in trainer_command:
trainer_command = trainer_command + ['--experiment_name', args.experiment_name]
memory_backend_params = None
if args.memory_backend == "redispubsub":
memory_backend_params = RedisPubSubMemoryBackendParameters()
ds_params_instance = None
if args.data_store == "s3":
ds_params = DataStoreParameters("s3", "", "")
ds_params_instance = S3DataStoreParameters(ds_params=ds_params, end_point=args.s3_end_point, bucket_name=args.s3_bucket_name,
creds_file=args.s3_creds_file, checkpoint_dir=ckpt_inside_container)
elif args.data_store == "nfs":
ds_params = DataStoreParameters("nfs", "kubernetes", "")
ds_params_instance = NFSDataStoreParameters(ds_params)
worker_run_type_params = RunTypeParameters(args.image, rollout_command, run_type=str(RunType.ROLLOUT_WORKER), num_replicas=args.num_workers)
trainer_run_type_params = RunTypeParameters(args.image, trainer_command, run_type=str(RunType.TRAINER))
orchestration_params = KubernetesParameters([worker_run_type_params, trainer_run_type_params],
kubeconfig='~/.kube/config',
memory_backend_parameters=memory_backend_params,
data_store_params=ds_params_instance)
orchestrator = Kubernetes(orchestration_params)
if not orchestrator.setup():
print("Could not setup.")
return
if orchestrator.deploy_trainer():
print("Successfully deployed trainer.")
else:
print("Could not deploy trainer.")
return
if orchestrator.deploy_worker():
print("Successfully deployed rollout worker(s).")
else:
print("Could not deploy rollout worker(s).")
return
try:
orchestrator.trainer_logs()
except KeyboardInterrupt:
pass
orchestrator.undeploy()
def handle_distributed_coach_orchestrator(args):
from rl_coach.orchestrators.kubernetes_orchestrator import KubernetesParameters, Kubernetes, \
RunTypeParameters
ckpt_inside_container = "/checkpoint"
arg_list = sys.argv[1:]
try:
i = arg_list.index('--distributed_coach_run_type')
arg_list.pop(i)
arg_list.pop(i)
except ValueError:
pass
trainer_command = [
'python3', 'rl_coach/coach.py', '--distributed_coach_run_type',
str(RunType.TRAINER)
] + arg_list
rollout_command = [
'python3', 'rl_coach/coach.py', '--distributed_coach_run_type',
str(RunType.ROLLOUT_WORKER)
] + arg_list
if '--experiment_name' not in rollout_command:
rollout_command = rollout_command + [
'--experiment_name', args.experiment_name
]
if '--experiment_name' not in trainer_command:
trainer_command = trainer_command + [
'--experiment_name', args.experiment_name
]
memory_backend_params = None
if args.memory_backend == "redispubsub":
memory_backend_params = RedisPubSubMemoryBackendParameters()
ds_params_instance = None
if args.data_store == "s3":
ds_params = DataStoreParameters("s3", "", "")
ds_params_instance = S3DataStoreParameters(
ds_params=ds_params,
end_point=args.s3_end_point,
bucket_name=args.s3_bucket_name,
creds_file=args.s3_creds_file,
checkpoint_dir=ckpt_inside_container,
expt_dir=args.experiment_path)
elif args.data_store == "nfs":
ds_params = DataStoreParameters("nfs", "kubernetes", "")
ds_params_instance = NFSDataStoreParameters(ds_params)
worker_run_type_params = RunTypeParameters(args.image,
rollout_command,
run_type=str(
RunType.ROLLOUT_WORKER),
num_replicas=args.num_workers)
trainer_run_type_params = RunTypeParameters(args.image,
trainer_command,
run_type=str(RunType.TRAINER))
orchestration_params = KubernetesParameters(
[worker_run_type_params, trainer_run_type_params],
kubeconfig='~/.kube/config',
memory_backend_parameters=memory_backend_params,
data_store_params=ds_params_instance)
orchestrator = Kubernetes(orchestration_params)
if not orchestrator.setup():
print("Could not setup.")
return 1
if orchestrator.deploy_trainer():
print("Successfully deployed trainer.")
else:
print("Could not deploy trainer.")
return 1
if orchestrator.deploy_worker():
print("Successfully deployed rollout worker(s).")
else:
print("Could not deploy rollout worker(s).")
return 1
if args.dump_worker_logs:
screen.log_title("Dumping rollout worker logs in: {}".format(
args.experiment_path))
orchestrator.worker_logs(path=args.experiment_path)
exit_code = 1
try:
exit_code = orchestrator.trainer_logs()
except KeyboardInterrupt:
pass
orchestrator.undeploy()
return exit_code