Skip to content

[Bugfix] Fix PrometheusStatsLogger crash on re-instantiation and non-daemon thread #905

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
SuperMarioYL wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

[Bugfix] Fix PrometheusStatsLogger crash on re-instantiation and non-daemon thread #905

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
18 changes: 12 additions & 6 deletions ucm/observability.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,12 +66,16 @@ def __init__(self, model_name, worker_id, config_path):
Load metrics config from YAML file (config_path),
register metrics using prometheus_client, and start a thread to get updated metrics.
"""
# Always initialize instance attributes so that shutdown() and
# __del__() work even when we skip metric registration below.
self.config = self._load_config(config_path)
self.log_interval = self.config.get("log_interval", 10)
self.is_running = False
self.thread = None

if _metric_mappings:
logger.warning("Metrics are already registered, skipping re-registration.")
return
# Load metrics config
self.config = self._load_config(config_path)
self.log_interval = self.config.get("log_interval", 10)

# Set up histogram max length
histogram_max_length = self.config.get("histogram_max_length", 10000)
Expand All @@ -97,9 +101,10 @@ def __init__(self, model_name, worker_id, config_path):
# Initialize metrics based on config
self._init_metrics_from_config()

# Start thread to update metrics
# Start daemon thread to update metrics so it won't block
# process exit if shutdown() is not explicitly called.
self.is_running = True
self.thread = threading.Thread(target=self.update_stats_loop)
self.thread = threading.Thread(target=self.update_stats_loop, daemon=True)
self.thread.start()

def _register_metrics_by_type(self, metric_type):
Expand Down Expand Up @@ -190,7 +195,8 @@ def update_stats_loop(self):

def shutdown(self):
self.is_running = False
self.thread.join()
if self.thread is not None:
self.thread.join()

def __del__(self):
try:
Expand Down
Loading