Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Unable to open shared memory region #7887

Open
zjhong12581 opened this issue Dec 17, 2024 · 0 comments
Open

Unable to open shared memory region #7887

zjhong12581 opened this issue Dec 17, 2024 · 0 comments

Comments

@zjhong12581
Copy link

Description
I want to use shm for inference. I have followed quickstart.md from docs but I'm not able to use shm.

Triton Information
I'm using tritonserver:24.11-py3 server and tritonserver:24.11-py3-sdk images.

Are you using the Triton container or did you build it yourself?

I'm using Triton container.

To Reproduce

I have downloaded model repository and used below command to run the triton.
docker run --gpus=1 --rm --ipc=host --net=host --shm-size 8G -v ${PWD}/model_repository:/models nvidia/tritonserver:24.11-py3 tritonserver --log-verbose=1 --model-repository=/models

I have used this command below to run sdk container.
docker run -it --rm --net=host nvidia/tritonserver:24.11-py3-sdk bash

In sdk container, /workspace/install/bin/simple_http_shm_client I have used previous command.
image

Got an error - {"error":"Unable to open shared memory region: '/input_simple'"}
Creating new channel with url:localhost:8001
Unregistered all system shared memory regions
Unregistered all system shared memory regions
error: failed to register input shared memory region: Unable to open shared memory region: '/input_simple'

Please find the server log below.

I1217 01:54:57.149670 1 grpc_server.cc:152] "Process for SystemSharedMemoryUnregister, rpc_ok=1, 2 step START"
I1217 01:54:57.149690 1 grpc_server.cc:102] "Ready for RPC 'SystemSharedMemoryUnregister', 3"
I1217 01:54:57.149756 1 grpc_server.cc:152] "Process for SystemSharedMemoryUnregister, rpc_ok=1, 2 step COMPLETE"
I1217 01:54:57.149767 1 grpc_server.cc:358] "Done for SystemSharedMemoryUnregister, 2"
I1217 01:54:57.149900 1 grpc_server.cc:152] "Process for CudaSharedMemoryUnregister, rpc_ok=1, 2 step START"
I1217 01:54:57.149912 1 grpc_server.cc:102] "Ready for RPC 'CudaSharedMemoryUnregister', 3"
I1217 01:54:57.149944 1 grpc_server.cc:152] "Process for CudaSharedMemoryUnregister, rpc_ok=1, 2 step COMPLETE"
I1217 01:54:57.149953 1 grpc_server.cc:358] "Done for CudaSharedMemoryUnregister, 2"
I1217 01:54:57.150148 1 grpc_server.cc:152] "Process for SystemSharedMemoryRegister, rpc_ok=1, 2 step START"
I1217 01:54:57.150161 1 grpc_server.cc:102] "Ready for RPC 'SystemSharedMemoryRegister', 3"
I1217 01:54:57.150183 1 shared_memory_manager.cc:141] "shm_open failed, errno: 2"
I1217 01:54:57.150227 1 grpc_server.cc:152] "Process for SystemSharedMemoryRegister, rpc_ok=1, 2 step COMPLETE"
I1217 01:54:57.150234 1 grpc_server.cc:358] "Done for SystemSharedMemoryRegister, 2"

image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

No branches or pull requests

1 participant