From 9040acd1fc89d13e581b3d33f8fb3eee6057ce11 Mon Sep 17 00:00:00 2001
From: Robert Rosca <robert.rosca@xfel.eu>
Date: Fri, 13 May 2022 14:49:57 +0200
Subject: [PATCH] Improve xfel_calibrate process error logging
---
webservice/webservice.py | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/webservice/webservice.py b/webservice/webservice.py
index f15aefbae..3f9963729 100644
--- a/webservice/webservice.py
+++ b/webservice/webservice.py
@@ -238,14 +238,16 @@ def change_config(config, updated_config, instrument,
return yaml.safe_dump(new_conf, default_flow_style=False).encode()
-async def run_proc_async(cmd: List[str]) -> Tuple[int, bytes]:
+async def run_proc_async(cmd: List[str]) -> Tuple[Optional[int], bytes, bytes]:
"""Run a subprocess to completion using asyncio, capturing stdout
Returns the numeric exit code and stdout (bytes)
"""
- proc = await asyncio.create_subprocess_exec(*cmd, stdout=asyncio.subprocess.PIPE)
- stdout, _ = await proc.communicate()
- return proc.returncode, stdout
+ proc = await asyncio.create_subprocess_exec(
+ *cmd, stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.PIPE
+ )
+ stdout, stderr = await proc.communicate()
+ return proc.returncode, stdout, stderr
def slurm_status(filter_user=True):
@@ -479,9 +481,10 @@ async def run_action(job_db, cmd, mode, proposal, run, rid) -> str:
"""
if mode == "prod":
logging.info(" ".join(cmd))
- retcode, stdout = await run_proc_async(cmd)
+ retcode, stdout, stderr = await run_proc_async(cmd)
if retcode != 0:
logging.error(Errors.JOB_LAUNCH_FAILED.format(cmd, retcode))
+ logging.error(f"{stdout=}, {stderr=}")
return Errors.JOB_LAUNCH_FAILED.format(cmd, retcode)
if "DARK" in cmd:
@@ -741,12 +744,13 @@ async def get_slurm_nice(partition: str, instrument: str,
return 0 # Don't apply degressive priority on exfel.
# List all names for jobs running in the specified partition.
- returncode, job_names = await run_proc_async(
+ returncode, job_names, stderr = await run_proc_async(
['squeue', '-h', '-o', '%.20j', '-p', partition, '--me'])
if returncode != 0:
logging.error(f'Non-zero return code {returncode} from '
f'`squeue` upon counting number of jobs')
+ logging.warning(f"{stderr=}")
return 0 # Fallback if something went wrong.
# Base value depending on proposal type using cycle, assuming that
--
GitLab