Catch and retry on OSError when killing LSF jobs

larsevj · larsevj · commit 59ebfaf865eb · 2025-04-24T13:12:57.000+02:00
diff --git a/src/ert/scheduler/driver.py b/src/ert/scheduler/driver.py
@@ -117,6 +117,10 @@ async def _execute_with_retry(
                 )
             except FileNotFoundError as e:
                 return (False, str(e))
+            except OSError as e:
+                logger.error(str(e))
+                await asyncio.sleep(retry_interval)
+                continue
 
             stdout, stderr = await process.communicate(stdin)
 

Original file line number	Diff line number	Diff line change
`@@ -117,6 +117,10 @@ async def _execute_with_retry(`
`117`	`117`	`)`
`118`	`118`	`except FileNotFoundError as e:`
`119`	`119`	`return (False, str(e))`
	`120`	`+ except OSError as e:`
	`121`	`+ logger.error(str(e))`
	`122`	`+ await asyncio.sleep(retry_interval)`
	`123`	`+ continue`
`120`	`124`
`121`	`125`	`stdout, stderr = await process.communicate(stdin)`
`122`	`126`