Skip to content

Commit

Permalink
remove heartbeat report in monitor(replaced by impl in diagnosis_agent)
Browse files Browse the repository at this point in the history
  • Loading branch information
BalaBalaYi committed Jan 2, 2025
1 parent 011b550 commit 2cb2c45
Showing 1 changed file with 0 additions and 10 deletions.
10 changes: 0 additions & 10 deletions dlrover/python/elastic_agent/monitor/training.py
Original file line number Diff line number Diff line change
Expand Up @@ -123,19 +123,9 @@ def report_resource_with_step(self):
except Exception as e:
logger.warning(e)

def send_heartbeat(self):
try:
ts = int(time.time())
action = self._master_client.report_heart_beat(ts)
if action:
pass
except Exception:
logger.warning("Fail to report a heartbeat.")

def _periodically_report(self):
logger.info("Start training agent reporter.")
while True:
if self._group_rank == 0:
self.report_resource_with_step()
self.send_heartbeat()
time.sleep(15)

0 comments on commit 2cb2c45

Please sign in to comment.