Serverless worker failing - how do I stop it
I have a couple of questions. I use Runpod Serverless to power a ComfyUI API - it works well most of the time but today I noticed one of my serverless workers kept failing. The errors only occured with one of the workers, the others performed fine. Why would this be? and is there a way of terminating specific workers? also, how can I get notified if one of them is playing up?
Thanks!
13 Replies
Can you post the log and pod id here?
Unknown User•16mo ago
Message Not Public
Sign In & Join Server To View
zelboxshlxhhqn
Unknown User•16mo ago
Message Not Public
Sign In & Join Server To View
this worker stopped completing jobs from about 13:30 yesterday
trying to ascertain why so it doesn't happen again
Unknown User•16mo ago
Message Not Public
Sign In & Join Server To View
is restricted the GPU type so that specific worker is no longer running
others are working fine
Unknown User•16mo ago
Message Not Public
Sign In & Join Server To View
ok thanks for the tip on terminating workers.
Unknown User•16mo ago
Message Not Public
Sign In & Join Server To View
File "/comfyui/execution.py", line 151, in recursive_execute
Also from log, seems bunch of errors from this file on line 151, maybe take a look what it is trying to do and why it fails.
thanks! going to try and build docker image again and make it a little more robust