Serverless TimeoutError: "Failed to get job"
Issue:
Getting repeated
- Error:
- Happens even with 120s timeout, single request takes at max 20 sec. Configuration:
- Worker:
- GPU:
- GPU count: 1 - GPU Memory: 16 GB - Timeout:
Getting repeated
TimeoutError in RunPod Serverless with no clear cause (no GPU OOM or other errors).- Error:
Failed to get job. | Error Type: TimeoutError | Error Message: Runpod serverless- Happens even with 120s timeout, single request takes at max 20 sec. Configuration:
- Worker:
Serverless- GPU:
RTX-A4500- GPU count: 1 - GPU Memory: 16 GB - Timeout:
120s
- Max workers: 2
- Min workers: 0
- Ideal Timeout: 60 sec
- Execution Timeout: 120 sec
- Enable Flashboot: True
- Execution Time of single Request: max 20 sec
Above Error occurs when there's load on API. My current setup is below
AWS API-GateWay--> AWS Lambda Function ---> Runpod Serverless
I Integrated AWS Lambda Function for conversion of Raw Image into base64 string and vice versa.
What I'm doing Wrong? I have attached ScreenShots may be they help
3 Replies
@Burki
Escalated To Zendesk
The thread has been escalated to Zendesk!
Any endpoint id's? Let staff check your endpoint via ticket
You can probably ignore this if it is happening infrequently. The worker will auto retry to fetch jobs. Also other workers will pickup the jobs.