DeepStream 5.0.1 nvstreamdemux core dump after RGBA conversion

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

DGPU: T4
Docker: nvcr.io/nvidia/deepstream:5.0.1-20.09-devel
BUG

Hi Nvidia Team,

We are experiencing a blocking issue when upgrading our pipeline from DeepStream 4.0.2 to DeepStream 5.0.1: nvstreamdemux no longer works when using RGBA conversion, it produces a core dump.
RGBA conversion is mandatory when modifying image buffers like blurring before demuxing.

Some simple test cases to reproduce:

#1 Pipeline with RGBA conversion which produces a core dump:

nvstreammux nvbuf-memory-type=3 name=m batched-push-timeout=40000 batch-size=2 width=960 height=540 ! queue ! nvinfer batch-size=2 config-file-path=/path_to_model/trafficCamNet/config_infer_primary.txt ! queue ! nvvideoconvert nvbuf-memory-type=3 ! “video/x-raw(memory:NVMM), format=RGBA” ! nvstreamdemux name=demux demux.src_0 ! nvvideoconvert nvbuf-memory-type=3 ! nvdsosd ! nveglglessink qos= true sync=false async=false demux.src_1 ! nvvideoconvert nvbuf-memory-type=3 ! nvdsosd ! nveglglessink qos= true sync=false async=false uridecodebin uri=file:///opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p_h265.mp4 name=decodebin_0 ! m.sink_0 uridecodebin uri=file:///opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p_h265.mp4 name=decodebin_1 ! m.sink_1

#2 Same pipeline with NV12 which works properly :

nvstreammux nvbuf-memory-type=3 name=m batched-push-timeout=40000 batch-size=2 width=960 height=540 ! queue ! nvinfer batch-size=2 config-file-path=/path_to_model/trafficCamNet/config_infer_primary.txt ! queue ! nvvideoconvert nvbuf-memory-type=3 ! “video/x-raw(memory:NVMM), format=NV12” ! nvstreamdemux name=demux demux.src_0 ! nvvideoconvert nvbuf-memory-type=3 ! nvdsosd ! nveglglessink qos= true sync=false async=false demux.src_1 ! nvvideoconvert nvbuf-memory-type=3 ! nvdsosd ! nveglglessink qos= true sync=false async=false uridecodebin uri=file:///opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p_h265.mp4 name=decodebin_0 ! m.sink_0 uridecodebin uri=file:///opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p_h265.mp4 name=decodebin_1 ! m.sink_1

3# Pipeline with double conversion NV12 → RGBA → NV12 witch also produces a core dump :

nvstreammux nvbuf-memory-type=3 name=m batched-push-timeout=40000 batch-size=2 width=960 height=540 ! queue ! nvinfer batch-size=2 config-file-path=/path_to_model/trafficCamNet/config_infer_primary.txt ! queue ! nvvideoconvert nvbuf-memory-type=3 ! “video/x-raw(memory:NVMM), format=RGBA” ! queue ! nvvideoconvert nvbuf-memory-type=3 ! “video/x-raw(memory:NVMM), format=NV12” ! nvstreamdemux name=demux demux.src_0 ! nvvideoconvert nvbuf-memory-type=3 ! nvdsosd ! nveglglessink qos= true sync=false async=false demux.src_1 ! nvvideoconvert nvbuf-memory-type=3 ! nvdsosd ! nveglglessink qos= true sync=false async=false uridecodebin uri=file:///opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p_h265.mp4 name=decodebin_0 ! m.sink_0 uridecodebin uri=file:///opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_1080p_h265.mp4 name=decodebin_1 ! m.sink_1

All these tests were running perfectly with nvcr.io/nvidia/deepstream:4.0.2-19.12-devel

Please address this issue as a major one.

3

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

4

Hi Fiona,

Here is the required information:

• Hardware Platform (Jetson / GPU) : GPU T4
• DeepStream Version : 5.0.1
• JetPack Version (valid for Jetson only) : NA
• TensorRT Version : 7.0.0 / CUDA 10.2
• NVIDIA GPU Driver Version (valid for GPU only): 440.100
• Issue Type( questions, new requirements, bugs) : BUG
**• 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): See description
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description): DeepStream SDK 5.0.1 nvstreamdemux

5

I can reproduce the problem. We will debug this problem and response when there is any progress.

6

Ok Fiona, perfect. We’ll be waiting for your feedback.

7

@alexandre.reboul The develop team has an internal bug to track this issue.

1 Like
9

Hi Fiona, any news about this issue ? We’re still blocked on our side until you provide a fix. Thanks in advance !

10

@alexandre.reboul We have fixed this bug and the solution will be available with next release.

11

Perfect ! Can you provide us a quick fix sending us the patched DS filters for DGPU / Jetson to unlock us ? Or maybe the next release is about to be delivered ?

12

Hi,
We are also getting some weird behaviour with demux in deepstream 5.0.1. Basically, out pipeline works with nvmultistreamtiler but not with demux, so I suspect this bug is affecting us too.
When is the next release with this bug fix planned? If there is a patch available we would also appreciate that too.
Thanks

13

The patch is under testing now. We will publish it ASAP.

2 Likes
14

Hi Fiona, any news on the patch release?

1 Like
15

Hi Fiona, can you give us some feedback on this issue? We reported it almost 3 months ago and the patch was being tested in November. This fix is extremely important to us because it prevents us from releasing our new software version to our customers.

16

Currently the release plan is in Feb.

2 Likes