0

I was running a Nvidia deepstream container on one of the GPU worker nodes in kubernetes cluster which is deployed as a job and below is my YAML file,

 apiVersion: batch/v1
kind: Job
metadata:
  name: deepstream-test
spec:
  backoffLimit: 1
  template:
    spec:
      containers:
        - name: nvidia-deepstream
          image: lkkrishna945/deepstream-5.0:test
          command: ["deepstream-app","-c","/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8_edited.txt"]
          ports:
            - containerPort: 8554
          resources:
            limits:
              nvidia.com/gpu: 1
      restartPolicy: Never

After I deployed this job it is running fine but the output of this is running on one of the worker nodes of on-perm opensource kubernetes cluster but I wanted to stream that running output which is a video.

Here's my Dockerfile which is built using base Nvidia deepstream container,

FROM nvcr.io/nvidia/deepstream:5.0-dp-20.04-triton

ADD source30_1080p_dec_infer-resnet_tiled_display_int8_edited.txt /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/
CMD ["deepstream-app -c /samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8_edited.txt"]

Can anyone help with any suggestions/solution on this?

Leela Krishna Uppuluri
  • 1
  • 1

1 Answers1

0

If you are streaming the output via RTSP, then you need to expose the port to which you are streaming RTSP and then map the docker port with host port. Then you can tap to the RTSP stream.

Neeraj Gulia
  • 640
  • 8
  • 24