Merge pull request #1161 from BalaBalaYi/add_wait_for_gierror

add wait in service check
intelligent-machine-learning · Jun 18, 2024 · e0e095f · e0e095f
2 parents 7fca2ba + 3a94a55
commit e0e095f
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/dlrover/python/master/scaler/pod_scaler.py b/dlrover/python/master/scaler/pod_scaler.py
@@ -503,9 +503,10 @@ def _check_master_service_avaliable(self, host, port, timeout=15):
  except socket.gaierror:
  logger.warning(
  f"Attempt {i}: Encountered gaierror while "
- f"performing master service check."
+ f"performing master service check. "
+ f"Service may not be available."
  )
- return False
+ time.sleep(1)
  except Exception as e:
  logger.warning(
  f"Attempt {i}: Encountered {str(e)} while "