server
server copied to clipboard
tritonclient.utils.InferenceServerException: [StatusCode.INTERNAL] Unable to open shared memory region: '/tVHIApxKugk6TwsknLr1b'
I try to create share_memory on client and got that error: here is my source code
self.shm_ip0_handle = shm.create_shared_memory_region("input0_data",
self.key1,
100)
self.shm_ip1_handle = shm.create_shared_memory_region("input1_data",
self.key2,
100)
input0_data_serialized = utils.serialize_byte_tensor(in0n)
input0_byte_size = utils.serialized_byte_size(input0_data_serialized)
shm.set_shared_memory_region(self.shm_ip0_handle, [input0_data_serialized])
self.triton_client.register_system_shared_memory("input0_data",
self.key1,
input0_byte_size)
input1_data_serialized = utils.serialize_byte_tensor(loc)
input1_byte_size = utils.serialized_byte_size(input1_data_serialized)
shm.set_shared_memory_region(self.shm_ip1_handle, [input1_data_serialized])
self.triton_client.register_system_shared_memory("input1_data",
self.key2,
input1_byte_size)
inputs[0].set_shared_memory("input0_data")
inputs[1].set_shared_memory("input1_data")
Hi @manhtd98, did the client code ran successfully? Can you share the entire server output?
it cannot pass to server. I got this error on client:
tritonclient.utils.InferenceServerException: [StatusCode.INTERNAL] Unable to open shared memory region: '/tVHIApxKugk6TwsknLr1b'
Are you running the client in a different container? If yes, you need to add --ipc host
flag to both of the containers.
i run client in host and triton on docker. I set --ipc host
on triton
Closing due to inactivity. Please let us know if you would like this issue reopened for follow-up.