Updated serverless workers are all unhealthy
I used to have a fully functional deployment of a serverless worker with comfyui which gets models from my network volume. I have since deployed an update which has new comfyui nodes and models, but my deployment only makes unhealthy workers and api requests are not being processed. I am not sure if the issue is my comfyui snapshot file that teh worker is building from, or the docker file build commands or my network volume. I need help. The worker that used to work is from this docker image fairweather7/runpod-comfyui-api-worker:1.0.5 and the new one that does not work is from fairweather7/runpod-comfyui-api-worker:1.0.11
3 Replies
Hi Mark,
I had a similar issue when there was a bug in the worker’s code that caused it to fail. After several failed attempts to run, the worker would become unhealthy.
Also, according to the docs, exit code 127 means: executable not found. So please double-check the template you’re using to run the worker.
Hello Eugene, thank you so much. I changed the executable command and the error changed to this. I am not sure if this counts as progress because on Googling I found that this meant - "When a RunPod worker exits with exit code 2, it typically indicates that there was a problem with the application's initialization or command execution. "
Unknown User•5mo ago
Message Not Public
Sign In & Join Server To View