def run(cls, role, console, **kwargs):
sys.stderr = open(os.devnull, "w")
cls.logger = logging.getLogger("gfl")
with Daemonizer() as (is_setup, daemonizer):
main_pid = None
if is_setup:
main_pid = os.getpid()
pid_file = PathUtils.join(GflConf.home_dir, "proc.lock")
stdout_file = PathUtils.join(GflConf.logs_dir, "console_out")
stderr_file = PathUtils.join(GflConf.logs_dir, "console_err")
is_parent = daemonizer(pid_file,
stdout_goto=stdout_file,
stderr_goto=stderr_file)
if is_parent:
if console and main_pid == os.getpid():
Shell.startup()
GflNode.load_node()
if GflConf.get_property("net.mode") == "standalone":
client_number = GflConf.get_property(
"net.standalone.client_number")
for _ in range(len(GflNode.standalone_nodes), client_number):
GflNode.add_standalone_node()
ManagerHolder.default_manager = NodeManager(
node=GflNode.default_node, role="server")
for i in range(client_number):
client_manager = NodeManager(node=GflNode.standalone_nodes[i],
role="client")
ManagerHolder.standalone_managers.append(client_manager)
else:
ManagerHolder.default_manager = NodeManager(
node=GflNode.default_node, role=role)
# cls.__startup_node_managers()
HttpListener.start()
while HttpListener.is_alive():
time.sleep(2)
def setUp(self) -> None:
# GflNode.init_node()
GflNode.load_node()
node_server = GflNode.standalone_nodes[0]
node_client1 = GflNode.standalone_nodes[1]
node_client2 = GflNode.standalone_nodes[2]
self.node_manager_server = NodeManager(node=node_server, role="server")
self.node_manager_client1 = NodeManager(node=node_client1, role="client")
self.node_manager_client2 = NodeManager(node=node_client2, role="client")
# 创建job
self.job = generate_job()
# 创建job对应的拓扑
topology_config = TopologyConfig()
topology_config.with_train_node_num(2)
topology_config.with_server_nodes([node_server.address])
topology_config.with_client_nodes([node_client1.address, node_client2.address])
topology_config.with_index2node([node_server.address, node_client1.address, node_client2.address])
temp_topology_manager = CentralizedTopologyManager(topology_config)
temp_topology_manager.generate_topology()
# 保存job对应的拓扑
save_topology_manager(job_id=self.job.job_id, topology_manager=temp_topology_manager)
import os work_dir = os.path.dirname(os.path.dirname(__file__)) os.chdir(work_dir) from gfl.conf import GflConf from gfl.core.manager.node import GflNode GflConf.home_dir = "data" GflNode.load_node()