Is there a limit in the number of threads?

I have pods with different numbers of vcpus. I am running vllm. If I create too many vllm in parallel, I get errors like "can't create thread". Is there a parameter that limits the number of threads per pod?
13 Replies
Space Burger
Space BurgerOP10mo ago
OpenBLAS blas_thread_init: pthread_create failed for thread 57 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: RLIMIT_NPROC -1 current, -1 max
OpenBLAS blas_thread_init: pthread_create failed for thread 58 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: RLIMIT_NPROC -1 current, -1 max
OpenBLAS blas_thread_init: pthread_create failed for thread 59 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: RLIMIT_NPROC -1 current, -1 max
OpenBLAS blas_thread_init: pthread_create failed for thread 60 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: pthread_create failed for thread 57 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: RLIMIT_NPROC -1 current, -1 max
OpenBLAS blas_thread_init: pthread_create failed for thread 58 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: RLIMIT_NPROC -1 current, -1 max
OpenBLAS blas_thread_init: pthread_create failed for thread 59 of 64: Resource temporarily unavailable
OpenBLAS blas_thread_init: RLIMIT_NPROC -1 current, -1 max
OpenBLAS blas_thread_init: pthread_create failed for thread 60 of 64: Resource temporarily unavailable
This is the error I get
nevermind
nevermind10mo ago
Yes, it has limit, I faced same issue I think I faced this problem at 1024 conc processes (means threads). You can always test it with thread swarming on pod
Space Burger
Space BurgerOP10mo ago
Thanks. Yeah the problem is that I get it with just 20 vllm in parallel. What do you mean by thread swarming? Should I just spin off a number of threads to see what the limit is?
Unknown User
Unknown User10mo ago
Message Not Public
Sign In & Join Server To View
Space Burger
Space BurgerOP10mo ago
Yeah. I am running 20 vllms in different screen
Unknown User
Unknown User10mo ago
Message Not Public
Sign In & Join Server To View
Space Burger
Space BurgerOP10mo ago
With vllm serve
Unknown User
Unknown User10mo ago
Message Not Public
Sign In & Join Server To View
Space Burger
Space BurgerOP10mo ago
Yes for some pod I can run like 19 in parallel and for some like 28. It is related to the number of vcpu. But I don't understand how it is related. I would be happy to run 64 say in parallel. At some point I am hitting ram and vram limits. But that is OK. I don't understand why I am hitting multithread limits when there is still ram and vram available.
Unknown User
Unknown User10mo ago
Message Not Public
Sign In & Join Server To View
Space Burger
Space BurgerOP10mo ago
Yeah definitely. But like it should still multithread in time sharing. E.g. Even with 1 vcpu I should be able to get 10 threads. But here it seems that I can get max 2 threads per vcpu
Unknown User
Unknown User10mo ago
Message Not Public
Sign In & Join Server To View
Poddy
Poddy10mo ago
@Space Burger
Escalated To Zendesk
The thread has been escalated to Zendesk!
Ticket ID: #11,317

Did you find this page helpful?