DeepStream video analysis demo chart v0.1.19 Failed to connect

[robert.tsai]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)

L4
• DeepStream Version

DeepStream helm chart doc v0.1.9

https://catalog.ngc.nvidia.com/orgs/nvidia/helm-charts/video-analytics-demo?version=0.1.9

• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)

I followed the documentation to deploy the chart on a 3-node Kubernetes cluster with an L4 GPU. The deployment steps are listed below.

I would like to ask DeepStream experts for advice or suggestions on how to resolve the issue where the demo video cannot be played. Any feedback would be greatly appreciated. Thank you.

Issue1: visit demo UI url, no stream/video show up

$ echo http://$NODE_IP:$ANT_NODE_PORT

http://172.27.119.46:31115

Issue2: logs with error and warning

$ kubectl logs nvdsdemo-video-analytics-demo-6488777549-t6z5m
…
**PERF: FPS 0 (Avg)
**PERF: 0.00 (0.00)
…
ERROR from src_elem0: Could not open resource for reading and writing.
Debug info: gstrtspsrc.c(7893): gst_rtspsrc_retrieve_sdp (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin0/GstRTSPSrc:src_elem0:
Failed to connect. (Generic error)
…
(deepstream-app:1352): GLib-GObject-WARNING **: 02:38:17.280: g_object_get_is_valid_property: object class ‘GstUDPSrc’ has no property named ‘pt’
…

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

Deploy the chart
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

DeepStream helm chart doc v0.1.9

GPU-optimized AI, Machine Learning, & HPC Software | NVIDIA NGC | NVIDIA NGC

Deployment steps:

1. Download chart
   helm fetch https://helm.ngc.nvidia.com/nvidia/charts/video-analytics-demo-0.1.9.tgz

2. update the values.yaml

cameras:
camera1: rtsp://172.27.112.82:8554/taipei

$ kubectl get po -o wide
NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES
nvdsdemo-video-analytics-demo-6488777549-t6z5m 1/1 Running 0 20h 10.42.1.88 ks-9296674
nvdsdemo-video-analytics-demo-webui-78b68db55b-nqvn8 2/2 Running 0 20h 10.42.2.54 ks-9292828

run “nvidia-smi -l” command in the 1st pod

Tue Mar 17 02:54:34 2026
±----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.82.09 Driver Version: 580.82.09 CUDA Version: 13.0 |
±----------------------------------------±-----------------------±---------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA L4 Off | 00000000:C1:00.0 Off | 0 |
| N/A 48C P0 28W / 72W | 362MiB / 23034MiB | 0% Default |
| | | N/A |
±----------------------------------------±-----------------------±---------------------+

±----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 1352 C deepstream-app 354MiB |
±----------------------------------------------------------------------------------------+

ps: It’s no problem to view the camera1 steaming using VLC

[junshengy]

1. This is a legacy chart base on DS-6.2. If you want to deploy it by helm, try to override these two files.
   I update it to DS-8.0.
   deployment.yaml (7.3 KB)
   values.yaml (2.3 KB)

After the service starts, you can open this url in browser to check results . http://host_ip:31115

Like this:

2.You also can try it through deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display.txt. This is the backend implementation of the service.

3.Additionally, ensure that the IP address is accessible within the Pod; 172.xx.xx.xxx may not be accessible within the container. You can try publishing the stream to the host IP address.

@robert.tsai

camera1: rtsp://172.27.112.82:8554/taipei

[robert.tsai]

Thank you for the prompt reply. I will try deploying again using the attached deployment.yaml and values.yaml and will update the results afterward.

[robert.tsai]

It has been identified that the issue was caused by the video analytics pod not being able to access the IP camera. It is now working properly. Thank you for the guidance.

By the way, are there any recommended metrics to measure the performance of the streaming analytics? For example, latency, accuracy, number of streams, GPU utilization, GPU temperature, etc. Any insights would be greatly appreciated.

[junshengy]

You can refer to these two FAQs to obtain the pipeline’s FPS/latency.

Since your current application uses deepstream-app as the backend, this should be fairly easy to implement. However, I recommend using local files for testing, as network streaming may cause gaps in latency/fps testing due to delays.

DeepStream SDK FAQ

7. [DS 5.0GA_All_App] Enable Latency measurement for deepstream sample apps If you are using deepstream-app, to check the component latency directly, you need to set the env export NVDS_ENABLE_COMPONENT_LATENCY_MEASUREMENT=1 export NVDS_ENABLE_LATENCY_MEASUREMENT=1 If you are using other deepstream sample apps such as deepstream-test3, you need to apply the following patch and set the env export NVDS_ENABLE_COMPONENT_LATENCY_MEASUREMENT=1 export NVDS_ENABLE_LATENCY_MEASUREMENT=1 …

DeepStream SDK FAQ

8. [DS 5.0GA_All_App] Enable Perf measurement(FPS) for deepstream sample apps If you are using deepstream-app, you can add enable-perf-measurement=1 under Application Group in the config file If you are using other deepstream sample apps such as deepstream-test2, you can apply following patch to enable it diff --git a/sources/apps/sample_apps/deepstream-test2/deepstream_test2_app.c b/sources/apps/sample_apps/deepstream-test2/deepstream_test2_app.c index a2231acf535b4826adb766ed28f3aa80294c7f…

@robert.tsai

GPU utilization, GPU temperature, etc.

This data can be monitored through nvidia-smi

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks.