My serverless endpoint threw an error, but job remained in the queue and new endpoints were started to process it. I was away from my desk for lunch and my account balance got drained.
Is this the expected behaviour?
#My serverless endpoint threw an error, the queue of jobs didn't get cleared, credit drained
sudden cedar
Also am not sure how to access logs of the actual process that errored? I can see logs of the latest serverless instances that started up but no error messages there.
sudden cedar
oops. Error was obvious when I looked. Somehow the insert code changes from copilot chat resulted in lots of code duplication. And there were 2 calls to:
runpod.serverless.start({
"handler": handler
})
in my script which would explain the repetitive running! Haha.