R
RunPod10mo ago
ssssteven

error starting: Error response from daemon: Container aa58de3216b8515a3ee78aa46d9102331aaaf6c210a36c

Hey all, all my requests stopped working on p45dj1lfott9ob. Example: 2319a9c9-dccd-4930-b34f-0acce67bdc3c-u1 Example: 40c01e77-32c9-451e-ac7a-dc134b513a97-u1 Can someone helped me look into why this is happending? Thanks
39 Replies
Jason
Jason10mo ago
request id wont help Whats up, any logs? or errors (in text please)
ssssteven
sssstevenOP10mo ago
there's no logs. all requests are put into delay state.
Jason
Jason10mo ago
delay? no running worrkers?
ssssteven
sssstevenOP10mo ago
No description
Jason
Jason10mo ago
did you you use any from quick deploy? let me see the full page.. the worker part too
ssssteven
sssstevenOP10mo ago
it just delay infinitely
Jason
Jason10mo ago
?
ssssteven
sssstevenOP10mo ago
No description
ssssteven
sssstevenOP10mo ago
there's no logs
Jason
Jason10mo ago
*
ssssteven
sssstevenOP10mo ago
and the worker is in idle state
Jason
Jason10mo ago
I don't know whats wrong, did your code ever worked before?
ssssteven
sssstevenOP10mo ago
yes
Jason
Jason10mo ago
it just happened today or now?
ssssteven
sssstevenOP10mo ago
it just happened suddenly with that error message
Jason
Jason10mo ago
after worker running that, it stopped, and you sent request again it didn't run again?
ssssteven
sssstevenOP10mo ago
yes
Jason
Jason10mo ago
whats the worker doing
ssssteven
sssstevenOP10mo ago
it's custom rendering pipeline
Jason
Jason10mo ago
How do you call your serverless.start() in your code
ssssteven
sssstevenOP10mo ago
if name == 'main': runpod.serverless.start({ "handler": predict, "return_aggregate_stream": True, }) async def predict(job: Dict): // code even I killed the worker, the container loading seems to get stuck
ssssteven
sssstevenOP10mo ago
No description
Jason
Jason10mo ago
No its not stuck
ssssteven
sssstevenOP10mo ago
it has been like that for minutes now. It usually shows the docker pulling progress bar
Jason
Jason10mo ago
its still loading Thats downloading its only loading
ssssteven
sssstevenOP10mo ago
ok
Jason
Jason10mo ago
Wait so, you killed or removed the worker and now there is no more workers so your request become delayed thats normal...
ssssteven
sssstevenOP10mo ago
sorry I killed the worker after I could not figure out what's going on
Jason
Jason10mo ago
Killed how?
ssssteven
sssstevenOP10mo ago
RP web interface -> terminate
Jason
Jason10mo ago
maybe* it was running and you killed it okay..
ssssteven
sssstevenOP10mo ago
i don't know it was running. It's not taking any requests
Jason
Jason10mo ago
oh you only have 1 workers? try 3 max workers
ssssteven
sssstevenOP10mo ago
yeah it's a dev server
Jason
Jason10mo ago
tell me after, when it loads use 3 anyways
ssssteven
sssstevenOP10mo ago
I can't becaue the max 5 limit oh nvm, I can Trying it now
digigoblin
digigoblin10mo ago
Even if you have a max 5 limit, add credits and increase your worker count, you should never set max workers to 1 UNDER ANY CIRCUMSTANCES. RunPod set the default to 3, don't change it!
ssssteven
sssstevenOP10mo ago
got it.. thank you all. I also suggested maybe a warning message to prevent users not setting it below 3... otherwise, I think new users might miss it
digigoblin
digigoblin10mo ago
I logged it in #🧐|feedback as well https://discord.com/channels/912829806415085598/1256993229115625603 But yeah, maybe a big red warning or something can do rather than just preventing it outright

Did you find this page helpful?