Skip to content

Scheduler Logging Nits #1991

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: dev/v0.7.0
Choose a base branch
from
Open

Scheduler Logging Nits #1991

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions python/fedml/computing/scheduler/comm_utils/job_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
from fedml.computing.scheduler.slave.client_data_interface import FedMLClientDataInterface
from fedml.core.common.singleton import Singleton
from fedml.computing.scheduler.comm_utils.container_utils import ContainerUtils
from typing import List
from typing import List, Optional
import threading
import json

Expand Down Expand Up @@ -150,7 +150,7 @@ def balance_available_gpu_ids(available_gpu_ids):
return available_gpu_ids.copy()

@staticmethod
def request_gpu_ids(request_gpu_num, available_gpu_ids):
def request_gpu_ids(request_gpu_num, available_gpu_ids) -> (Optional[str], Optional[int]):
available_gpu_count = len(available_gpu_ids)
request_gpu_num = 0 if request_gpu_num is None else request_gpu_num
matched_gpu_num = min(available_gpu_count, request_gpu_num)
Expand Down
2 changes: 1 addition & 1 deletion python/fedml/computing/scheduler/master/server_login.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -384,7 +384,7 @@ def init_logs(args, edge_id):
args.edge_id = edge_id
setattr(args, "using_mlops", True)
setattr(args, "server_agent_id", edge_id)
MLOpsRuntimeLog.get_instance(args).init_logs()
MLOpsRuntimeLog.get_instance(args).init_logs(log_level=logging.INFO)


def login(args):
Expand Down
3 changes: 1 addition & 2 deletions python/fedml/computing/scheduler/slave/client_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -907,7 +907,7 @@ def ota_upgrade(self, payload, request_json):

def callback_start_train(self, topic, payload):
# Get training params

MLOpsRuntimeLog.get_instance(self.args).init_logs(log_level=logging.INFO)
request_json = json.loads(payload)
is_retain = request_json.get("is_retain", False)
if is_retain:
Expand All @@ -918,7 +918,6 @@ def callback_start_train(self, topic, payload):
train_edge_id = str(topic).split("/")[-2]
self.args.run_id = run_id
self.args.edge_id = train_edge_id
MLOpsRuntimeLog.get_instance(self.args).init_logs(log_level=logging.INFO)
MLOpsRuntimeLogDaemon.get_instance(self.args).start_log_processor(
run_id, train_edge_id, log_source=SchedulerConstants.get_log_source(request_json))
logging.info("start the log processor")
Expand Down
2 changes: 1 addition & 1 deletion python/fedml/core/mlops/mlops_runtime_log.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,7 +241,7 @@ def build_log_file_path_with_run_params(
args = parser.parse_args()
setattr(args, "using_mlops", True)
setattr(args, "config_version", "local")
MLOpsRuntimeLog.get_instance(args).init_logs()
MLOpsRuntimeLog.get_instance(args).init_logs(log_level=logging.INFO)

count = 0
while True:
Expand Down