Runpod•13mo ago

API to remove worker from endpoint - please!

Sometimes one worker in endpoint fails because of internal errors, misconfiguration, out of space (because of memory purging errors) and etc (happens in less than 1%). Unfortunately this worker will generate endless errors and each task going to that worker will fail . So it is always a job to be done by logging in to account and manually kicking that worker out of endpoint to stop errors. Definitely need an API to be able to kick unhealthy workers from endpoints. 🙏

8 Replies

yhlong00000•13mo ago

you can use our graphql to terminate worker.

One@DRTOP•13mo ago

Thanks, can you help me finding that in your docs please, I see only WorkerState - https://graphql-spec.runpod.io/#definition-WorkerState As i am looking to terminate the worker inside serverless.

yhlong00000•13mo ago

mutation terminatePod($input: PodTerminateInput!) {
  podTerminate(input: $input)
}


{
  "input": {
    "podId": "23vja1jrs3d0h7"
  }
}

mutation terminatePod($input: PodTerminateInput!) {
  podTerminate(input: $input)
}


{
  "input": {
    "podId": "23vja1jrs3d0h7"
  }
}

One@DRTOP•13mo ago

thank you !!!

One@DRTOP•11mo ago

Can't make it work, have 500 Internal Server Error response. Important note that I am talking about serverless worker, not pod.

Unknown User•11mo ago

Message Not Public

One@DRTOP•11mo ago

the authorization was set up in auth part and that was the issue, thanks a lot!

Unknown User•11mo ago

Message Not Public

Gaming

Programming

API to remove worker from endpoint - please!

Did you find this page helpful?