Some more update,
animation-pipeline
workflow build
I was able to built the _build
directory via the following command:
$ ucf_app_builder_cli app build ucs_apps/animation_pipeline.yaml ucs_apps/animation_pipeline_params.yaml -o _build/animation_pipeline
2024-10-06 21:49:31,216 - AppBuilder - INFO - Syncing any missing service versions to cache...
2024-10-06 21:49:31,230 - AppBuilder - INFO - Validating application ...
2024-10-06 21:49:31,238 - AppBuilder - INFO - Building application animation-pipeline-1.0.1 ...
2024-10-06 21:51:04,628 - AppBuilder - INFO - Application Information written to _build/animation_pipeline/app_info.yaml
2024-10-06 21:51:04,765 - AppBuilder - INFO - Application compliance report generated at _build/animation_pipeline/compliance_report.json
Application Helm Chart generated in _build/animation_pipeline
2024-10-06 21:51:04,766 - MsBuilder - INFO - App built
The good thing is that the ucf_app_builder_cli
was able to find my secrets for ngc-api-key-secret
in animation-pipeline
namespace.
However, upon my k8s deployment with helm
using this command:
$ helm upgrade --install --cleanup-on-fail --namespace $names
pace $name _build/animation_pipeline/ -f _build/animation_pipeline/values.yaml -f ucs_apps/animation_pipeline_values.yaml
WARNING: Kubernetes configuration file is group-readable. This is insecure. Location: /var/lib/k0s/pki/admin.conf
WARNING: Kubernetes configuration file is world-readable. This is insecure. Location: /var/lib/k0s/pki/admin.conf
Release "animation-pipeline" has been upgraded. Happy Helming!
NAME: animation-pipeline
LAST DEPLOYED: Sun Oct 6 21:54:06 2024
NAMESPACE: animation-pipeline
STATUS: deployed
REVISION: 2
TEST SUITE: None
The pod avatar-renderer-a-deployment-0
(also b deployment) was always restarting and I’m not sure why.
Here's the pods full logs:
+ ldconfig -p
+ grep libGLX_nvidia.so.0
libGLX_nvidia.so.0 (libc6,x86-64) => /usr/lib/x86_64-linux-gnu/libGLX_nvidia.so.0
+ [[ -v NOTFOUND ]]
+ export VK_ICD_FILENAMES=/tmp/nvidia_icd.json
+ VK_ICD_FILENAMES=/tmp/nvidia_icd.json
+ export LD_LIBRARY_PATH=:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/opt/nvidia/omniverse/kit-sdk-launcher/plugins/carb_gfx
+ LD_LIBRARY_PATH=:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/opt/nvidia/omniverse/kit-sdk-launcher/plugins/carb_gfx
+ /opt/nvidia/omniverse/vkapiversion/bin/vkapiversion /tmp/nvidia_icd.json
Writing disposable ICD file (/tmp/tmp_icd_B0uViW.json)...
Writing ICD file to (/tmp/nvidia_icd.json)
GPU0
apiVersion = 1.3.277
driverVersion = 550.54.15
vendorID = 0x10de
deviceID = 0x2330
deviceName = NVIDIA H100 80GB HBM3
++ echo False
++ tr '[:upper:]' '[:lower:]'
+ lowercase_gpu_disable_alloc=false
+ '[' false == true ']'
+ '[' false == 1 ']'
+ echo 'Dynamic GPU allocation disabled'
Dynamic GPU allocation disabled
+ export CUDA_VISIBLE_DEVICES=0
+ CUDA_VISIBLE_DEVICES=0
+ echo Running: --/exts/omni.services.transport.server.http/port=8021 --/app/printConfig=False --/app/window/width=1280 --/app/window/height=720 --enable omni.kit.telemetry --/crashreporter/enabled=true --/crashreporter/data/serviceName=ia-omniverse-renderer-microservice-a-deployment --/crashreporter/url=https://services.nvidia.com/submit --/crashreporter/alwaysUpload=true --/crashreporter/dumpDir=/home/ace/asset
Running: --/exts/omni.services.transport.server.http/port=8021 --/app/printConfig=False --/app/window/width=1280 --/app/window/height=720 --enable omni.kit.telemetry --/crashreporter/enabled=true --/crashreporter/data/serviceName=ia-omniverse-renderer-microservice-a-deployment --/crashreporter/url=https://services.nvidia.com/submit --/crashreporter/alwaysUpload=true --/crashreporter/dumpDir=/home/ace/asset
+ exec /opt/nvidia/omniverse/renderer/kit/kit /opt/nvidia/omniverse/renderer/apps/omni.omniverse_renderer_ms.app.kit --/persistent/app/viewport/defaults/tickRate=30 --ext-folder /opt/nvidia/omniverse/kit-livestream/ --no-window --/exts/omni.services.transport.server.http/port=8021 --/app/printConfig=False --/app/window/width=1280 --/app/window/height=720 --enable omni.kit.telemetry --/crashreporter/enabled=true --/crashreporter/data/serviceName=ia-omniverse-renderer-microservice-a-deployment --/crashreporter/url=https://services.nvidia.com/submit --/crashreporter/alwaysUpload=true --/crashreporter/dumpDir=/home/ace/asset
[Info] [carb] Logging to file: /home/ace/.nvidia-omniverse/logs/Kit/omni.omniverse_renderer_ms.app/0.0/kit_20241006_150416.log
[0.488s] [ext: omni.kit.async_engine-0.0.0] startup
[0.569s] [ext: omni.stats-0.0.0] startup
[0.571s] [ext: omni.assets.plugins-0.0.0] startup
[0.572s] [ext: omni.rtx.shadercache.vulkan-1.0.0] startup
[0.573s] [ext: omni.client-1.0.1] startup
[0.585s] [ext: omni.gpu_foundation-0.0.0] startup
[0.604s] [ext: carb.windowing.plugins-1.0.0] startup
2024-10-06 15:04:17 [583ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:17 [583ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
[0.605s] [ext: omni.kit.renderer.init-0.0.0] startup
2024-10-06 15:04:17 [636ms] [Warning] [omni.platforminfo.plugin] failed to open the default display. Can't verify X Server version.
|---------------------------------------------------------------------------------------------|
| Driver Version: 550.54.15 | Graphics API: Vulkan
|=============================================================================================|
| GPU | Name | Active | LDA | GPU Memory | Vendor-ID | LUID |
| | | | | | Device-ID | UUID |
| | | | | | Bus-ID | |
|---------------------------------------------------------------------------------------------|
| 0 | NVIDIA H100 80GB HBM3 | Yes: 0 | | 81559 MB | 10de | 0 |
| | | | | | 2330 | 61a1dd9b.. |
| | | | | | 19 | |
|=============================================================================================|
| OS: 20.04.6 LTS (Focal Fossa) ubuntu, Version: 20.04.6, Kernel: 5.15.0-122-generic
| Processor: Intel(R) Xeon(R) Platinum 8462Y+ | Cores: 64 | Logical: 128
|---------------------------------------------------------------------------------------------|
| Total Memory (MB): 2063919 | Free Memory: 1957812
| Total Page/Swap (MB): 0 | Free Page/Swap: 0
|---------------------------------------------------------------------------------------------|
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] ECC is enabled for device 0. This will reduce rendering performance.
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin]
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] -----------------------------------------------------------------------
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] !!!!! Local system validation failed! Incorrect configuration detected.
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] Summary below. Details above.
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] -----------------------------------------------------------------------
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin]
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] - ECC: FAILED
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] - IOMMU: OK
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin]
2024-10-06 15:04:19 [2,684ms] [Warning] [gpu.foundation.plugin] -----------------------------------------------------------------------
[3.113s] [ext: omni.kit.pipapi-0.0.0] startup
[3.118s] [ext: omni.kit.pip_archive-0.0.0] startup
[3.118s] [ext: omni.kit.telemetry-0.5.0] startup
[3.161s] [ext: omni.mtlx-0.1.0] startup
[3.162s] [ext: omni.usd.config-1.0.3] startup
[3.168s] [ext: omni.gpucompute.plugins-0.0.0] startup
[3.168s] [ext: omni.usd.libs-1.0.0] startup
[3.267s] [ext: omni.kit.loop-default-0.2.0] startup
[3.268s] [ext: omni.appwindow-1.1.5] startup
2024-10-06 15:04:20 [3,248ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:20 [3,248ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
[3.272s] [ext: omni.kit.renderer.core-0.0.0] startup
2024-10-06 15:04:20 [3,254ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:20 [3,254ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
2024-10-06 15:04:20 [3,263ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:20 [3,263ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
[3.286s] [ext: omni.kit.renderer.capture-0.0.0] startup
[3.289s] [ext: omni.kit.renderer.imgui-0.0.0] startup
2024-10-06 15:04:20 [3,271ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:20 [3,271ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
2024-10-06 15:04:20 [3,272ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:20 [3,272ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
2024-10-06 15:04:20 [3,273ms] [Warning] [carb.windowing-glfw.plugin] GLFW initialization failed.
2024-10-06 15:04:20 [3,273ms] [Warning] [carb] Failed to startup plugin carb.windowing-glfw.plugin (interfaces: [carb::windowing::IGLContext v1.0],[carb::windowing::IWindowing v1.4]) (impl: carb.windowing-glfw.plugin)
[3.439s] [ext: carb.audio-0.1.0] startup
[3.464s] [ext: omni.ui-2.18.6] startup
[3.485s] [ext: omni.uiaudio-1.0.0] startup
[3.487s] [ext: omni.kit.mainwindow-1.0.1] startup
[3.490s] [ext: omni.kit.uiapp-0.0.0] startup
[3.490s] [ext: omni.usd.schema.omniscripting-1.0.0] startup
[3.616s] [ext: omni.usd.schema.anim-0.0.0] startup
[3.658s] [ext: omni.usd.schema.omnigraph-1.0.0] startup
[3.670s] [ext: omni.usd.schema.audio-0.0.0] startup
[3.675s] [ext: omni.usd.schema.semantics-0.0.0] startup
[3.679s] [ext: omni.usd.schema.geospatial-0.0.0] startup
[3.683s] [ext: omni.usd.schema.physics-0.0.0] startup
[3.706s] [ext: omni.usd_resolver-1.0.1] startup
[3.711s] [ext: omni.usd.core-1.1.8] startup
[3.714s] [ext: omni.resourcemonitor-105.0.0] startup
[3.717s] [ext: omni.activity.core-1.0.1] startup
[3.719s] [ext: omni.hydra.usdrt_delegate-7.2.39] startup
[3.732s] [ext: omni.kit.audiodeviceenum-1.0.1] startup
[3.734s] [ext: omni.kit.widget.path_field-2.0.8] startup
[3.743s] [ext: omni.kit.actions.core-1.0.0] startup
[3.745s] [ext: omni.graph.exec-0.3.0] startup
[3.746s] [ext: omni.kit.widget.browser_bar-2.0.9] startup
[3.750s] [ext: omni.kit.commands-1.4.6] startup
[3.783s] [ext: omni.kit.exec.core-0.5.0] startup
[3.786s] [ext: omni.kit.viewport.registry-104.0.5] startup
[3.788s] [ext: omni.kit.menu.utils-1.5.7] startup
[3.816s] [ext: omni.kit.window.popup_dialog-2.0.23] startup
[3.826s] [ext: omni.timeline-1.0.9] startup
[3.829s] [ext: omni.kit.widget.nucleus_connector-1.1.4] startup
[3.842s] [ext: omni.hydra.scene_delegate-0.3.2] startup
[3.849s] [ext: omni.iray.libs-0.0.0] startup
[3.854s] [ext: omni.usd-1.10.21] startup
[3.965s] [ext: omni.mdl.neuraylib-0.2.0] startup
[3.967s] [ext: omni.kit.helper.file_utils-0.1.6] startup
[4.058s] [ext: omni.kit.widget.nucleus_info-1.0.2] startup
[4.060s] [ext: omni.volume-0.4.0] startup
[4.062s] [ext: omni.kit.widget.filebrowser-2.3.35] startup
[4.092s] [ext: omni.kit.search_core-1.0.5] startup
[4.095s] [ext: omni.hydra.rtx-0.1.0] startup
[4.111s] [ext: omni.kit.widget.search_delegate-1.0.4] startup
[4.118s] [ext: omni.kit.widget.version------------------SETTINGS------------------
scene_skel_root_prim_path: /World/SkelRoots/Rig_Retarget/SkelRoot
scene_skeleton_prim_path: /World/SkelRoots/Rig_Retarget/SkelRoot/Skeleton
scene_skel_animation_prim_path: /World/SkelRoots/Rig_Retarget/SkelRoot/Skeleton/ACE_Animation_Target
scene_camera_prim_path: /World/SkelRoots/Rig_Camera/SkelRoot/Skeleton/root/camera_location/camera_body/camera_main
scene_skel_roots_scope_prim_path: /World/SkelRoots
scene_character_anim_pose_prim_path: /World/SkelRoots/Rig_Retarget/SkelRoot/Skeleton/AnimGraphOutputPose
scene_path: /home/ace/asset/Avatar_Scene.usda
scene_validation_mode: SceneValidationMode.DEFAULT_SCENE_VALIDATION
animation_source_host: ia-animation-graph-microservice-deployment-service
animation_source_port: 51000
animation_source_buffer_size: 0.1
debug_log_enabled: True
debug_log_each_received_animation_data_message: False
debug_log_frame_interval: 30
debug_show_wheel: False
rtp_negotiation_host: 0.0.0.0
rtp_negotiation_port: 32667
rtp_negotiation_host_mocking_enabled: True
livestream_host: 127.0.0.1
livestream_video_port: 9020
livestream_video_bit_rate: 32777216
livestream_video_iframe_interval: 30
livestream_video_frame_rate: 30
livestream_audio_port: 9021
livestream_audio_sample_rate: 16000
livestream_audio_bit_rate: 32
/exts/omni.services.transport.server.http/port: 8021
--------------------------------------------
2024-10-06 15:04:21 [5,079ms] [Error] [carb] [Plugin: libomni.livestream-rtp_udp.plugin.so] Could not load the dynamic library from /opt/nvidia/omniverse/kit-livestream/omni.kit.livestream.rtp_udp/plugins/libomni.livestream-rtp_udp.plugin.so. Error: /opt/nvidia/omniverse/kit-livestream/omni.kit.livestream.rtp_udp/plugins/libssl.so.1.1: undefined symbol: EVP_idea_cbc, version OPENSSL_1_1_0 (Additional information may be available by running the process with the LD_DEBUG environment variable set)
2024-10-06 15:04:21 [5,079ms] [Error] [omni.ext.plugin] [ext: omni.kit.livestream.rtp_udp-1.0.0] failed to load native plugin: /opt/nvidia/omniverse/kit-livestream/omni.kit.livestream.rtp_udp/plugins/libomni.livestream-rtp_udp.plugin.so
ing-1.4.6] startup
[4.130s] [ext: omni.kit.hydra_texture-1.1.12] startup
[4.135s] [ext: omni.ui.scene-1.7.0] startup
[4.142s] [ext: omni.kit.notification_manager-1.0.6] startup
[4.148s] [ext: omni.kit.clipboard-1.0.3] startup
[4.149s] [ext: omni.kit.widget.viewport-105.1.10] startup
[4.171s] [ext: omni.kit.window.filepicker-2.10.14] startup
[4.249s] [ext: omni.kit.viewport.window-105.1.13] startup
[4.301s] [ext: omni.kit.window.file_importer-1.0.23] startup
[4.305s] [ext: omni.omniverse_renderer_ms.dependencies.pip-0.0.0] startup
[4.342s] [ext: omni.kit.viewport.utility-1.0.16] startup
[4.347s] [ext: omni.services.facilities.base-1.0.4] startup
[4.348s] [ext: omni.kit.widget.searchable_combobox-1.0.5] startup
[4.353s] [ext: omni.services.core-1.9.0] startup
[4.566s] [ext: omni.kit.window.file_exporter-1.0.23] startup
[4.569s] [ext: omni.kit.widget.settings-1.0.6] startup
[4.580s] [ext: omni.services.transport.server.base-1.1.1] startup
[4.581s] [ext: omni.rtx.window.settings-0.6.9] startup
[4.593s] [ext: omni.services.transport.server.http-1.3.0] startup
[4.688s] [ext: omni.kit.viewport.rtx-104.0.0] startup
[4.688s] [ext: omni.omniverse_renderer_ms.window-0.0.0] startup
[5.023s] [ext: omni.kit.usd.layers-2.1.27] startup
[5.060s] [ext: omni.kit.menu.create-1.0.11] startup
[5.064s] [ext: omni.kit.context_menu-1.6.8] startup
[5.077s] [ext: omni.kit.window.preferences-1.3.23] startup
[5.094s] [ext: omni.kit.renderer.cuda_interop-1.0.1] startup
[5.096s] [ext: omni.kit.livestream.core-1.0.4] startup
[5.097s] [ext: omni.kit.livestream.rtp_udp-1.0.0] startup
2024-10-06 15:04:21 [5,079ms] [Warning] [carb] Potential plugin preload failed: /opt/nvidia/omniverse/kit-livestream/omni.kit.livestream.rtp_udp/plugins/libomni.livestream-rtp_udp.plugin.so
2024-10-06 15:04:21 [5,079ms] [Error] [carb] [Plugin: omni.kit.livestream.plugin] Dependency: [carb::livestream::Vision v0.4] failed to be resolved.
2024-10-06 15:04:21 [5,080ms] [Error] [carb] [Plugin: omni.kit.livestream.plugin] Dependency: [carb::livestream::Vision v0.4] failed to be resolved.
2024-10-06 15:04:21 [5,080ms] [Error] [carb.scripting-python.plugin] RuntimeError: Failed to acquire interface: omni::kit::livestream::ILivestream (pluginName: nullptr)
At:
/opt/nvidia/omniverse/kit-livestream/omni.kit.livestream.rtp_udp/omni/kit/livestream/rtp_udp/extension.py(25): on_startup
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(164): _startup_ext
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/carb/profiler/__init__.py(85): wrapper
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(224): startup
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(328): startup_extension
PythonExtension.cpp::startup()(2): <module>
/opt/nvidia/omniverse/renderer/exts/omni.omniverse_renderer_ms.window/omni/omniverse_renderer_ms/window/livestream.py(64): initialize
/opt/nvidia/omniverse/renderer/exts/omni.omniverse_renderer_ms.window/omni/omniverse_renderer_ms/window/extension.py(254): on_startup
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(164): _startup_ext
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/carb/profiler/__init__.py(83): wrapper
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(224): startup
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(328): startup_extension
PythonExtension.cpp::startup()(2): <module>
2024-10-06 15:06:22 [5,823ms] [Error] [omni.ext.plugin] [ext: omni.kit.livestream.rtp_udp-1.0.0] Failed to startup python extension.
2024-10-06 15:06:22 [5,863ms] [Error] [carb] [Plugin: omni.kit.livestream.plugin] Dependency: [carb::livestream::Vision v0.4] failed to be resolved.
2024-10-06 15:06:22 [5,863ms] [Error] [carb] [Plugin: omni.kit.livestream.plugin] Dependency: [carb::livestream::Vision v0.4] failed to be resolved.
2024-10-06 15:06:22 [5,863ms] [Error] [carb.scripting-python.plugin] RuntimeError: Failed to acquire interface: omni::kit::livestream::ILivestream (pluginName: nullptr)
At:
/opt/nvidia/omniverse/renderer/exts/omni.omniverse_renderer_ms.window/omni/omniverse_renderer_ms/window/livestream.py(69): initialize
/opt/nvidia/omniverse/renderer/exts/omni.omniverse_renderer_ms.window/omni/omniverse_renderer_ms/window/extension.py(254): on_startup
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(164): _startup_ext
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/carb/profiler/__init__.py(85): wrapper
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(224): startup
/opt/nvidia/omniverse/kit-sdk-launcher/kernel/py/omni/ext/_impl/_internal.py(328): startup_extension
PythonExtension.cpp::startup()(2): <module>
2024-10-06 15:06:22 [5,863ms] [Error] [omni.ext.plugin] [ext: omni.omniverse_renderer_ms.window-0.0.0] Failed to startup python extension.
[SceneLoader] Attempting to delete USD cache directory: /home/ace/asset/Avatar_Scene.usda-cache.
[SceneLoader] Directory '/home/ace/asset/Avatar_Scene.usda-cache' not found.
[SceneLoader] SCENE LOADED: /home/ace/asset/Avatar_Scene.usda
[SceneLoader] Default scene validation completed!
[SceneLoader] Assets loaded.
[5.931s] [ext: omni.omniverse_renderer_ms.app-0.0.0] startup
[6.024s] app ready
2024-10-06 15:06:23 [6,319ms] [Warning] [rtx.neuraylib.plugin] [IRAY:RENDER] 1.1 IRAY rend warn : CUDA device 0 (NVIDIA H100 80GB HBM3): ECC is enabled, this will reduce rendering performance (it is strongly recommended to disable ECC with iray)
2024-10-06 15:06:57 [40,302ms] [Warning] [carb.scenerenderer-rtx.plugin] Scene has 4 lights and may render slowly. Enabling Sampled Direct Lighting is recommended
2024-10-06 15:06:58 [41,541ms] [Warning] [gpu.foundation.plugin] Requesting texture to use texture streaming, but the service isn't available.The texture will be created as a regular resource.
[114.765s] [ext: omni.omniverse_renderer_ms.app-0.0.0] shutdown
[114.765s] [ext: omni.kit.livestream.rtp_udp-1.0.0] shutdown
[114.767s] [ext: omni.kit.livestream.core-1.0.4] shutdown
[114.776s] [ext: omni.kit.window.preferences-1.3.23] shutdown
2024-10-06 15:08:11 [114,798ms] [Warning] [omni.ext._impl._internal] omni.kit.window.preferences-1.3.23 -> <class 'omni.kit.window.preferences.scripts.preferences_window.PreferencesExtension'>: extension object is still alive, something holds a reference on it. References: ["[0]:type: <class 'method'>, id: 140052192450368", "[1]:type: <class 'cell'>, id: 140054967696736", "[2]:type: <class 'frame'>, id: 140052193415712", "[3]:type: <class 'frame'>, id: 140052192352320", "[4]:type: <class 'frame'>, id: 140052192096432"]
[114.828s] [ext: omni.kit.context_menu-1.6.8] shutdown
[114.829s] [ext: omni.omniverse_renderer_ms.window-0.0.0] shutdown
[114.831s] [ext: omni.kit.viewport.rtx-104.0.0] shutdown
[114.831s] [ext: omni.rtx.window.settings-0.6.9] shutdown
[114.835s] [ext: omni.kit.window.file_importer-1.0.23] shutdown
[114.837s] [ext: omni.kit.window.file_exporter-1.0.23] shutdown
[114.838s] [ext: omni.kit.menu.create-1.0.11] shutdown
[114.839s] [ext: omni.kit.usd.layers-2.1.27] shutdown
[114.845s] [ext: omni.kit.viewport.utility-1.0.16] shutdown
[114.846s] [ext: omni.kit.viewport.window-105.1.13] shutdown
2024-10-06 15:08:11 [114,914ms] [Warning] [omni.ext._impl._internal] omni.kit.viewport.window-105.1.13 -> <class 'omni.kit.viewport.window.extension.ViewportWindowExtension'>: extension object is still alive, something holds a reference on it. References: ["[0]:type: <class 'frame'>, id: 150331824", "[1]:type: <class 'frame'>, id: 149617424", "[2]:type: <class 'frame'>, id: 140079357588128"]
[114.943s] [ext: omni.kit.widget.viewport-105.1.10] shutdown
[114.945s] [ext: omni.kit.hydra_texture-1.1.12] shutdown
[114.946s] [ext: omni.kit.window.filepicker-2.10.14] shutdown
[114.947s] [ext: omni.kit.widget.search_delegate-1.0.4] shutdown
[114.948s] [ext: omni.kit.widget.filebrowser-2.3.35] shutdown
[114.950s] [ext: omni.kit.helper.file_utils-0.1.6] shutdown
[114.951s] [ext: omni.usd-1.10.21] shutdown
[116.132s] [ext: omni.kit.uiapp-0.0.0] shutdown
[116.132s] [ext: omni.uiaudio-1.0.0] shutdown
[116.133s] [ext: omni.kit.audiodeviceenum-1.0.1] shutdown
[116.133s] [ext: carb.audio-0.1.0] shutdown
[116.133s] [ext: omni.kit.renderer.cuda_interop-1.0.1] shutdown
[116.134s] [ext: omni.ui.scene-1.7.0] shutdown
[116.135s] [ext: omni.kit.mainwindow-1.0.1] shutdown
[116.135s] [ext: omni.kit.widget.settings-1.0.6] shutdown
[116.135s] [ext: omni.kit.widget.browser_bar-2.0.9] shutdown
[116.136s] [ext: omni.kit.menu.utils-1.5.7] shutdown
[116.136s] [ext: omni.kit.notification_manager-1.0.6] shutdown
[116.137s] [ext: omni.kit.viewport.registry-104.0.5] shutdown
[116.137s] [ext: omni.kit.widget.path_field-2.0.8] shutdown
[116.137s] [ext: omni.kit.widget.versioning-1.4.6] shutdown
[116.138s] [ext: omni.kit.widget.searchable_combobox-1.0.5] shutdown
[116.138s] [ext: omni.kit.widget.nucleus_connector-1.1.4] shutdown
2024-10-06 15:08:13 [116,122ms] [Warning] [omni.ext._impl._internal] omni.kit.widget.nucleus_connector-1.1.4 -> <class 'omni.kit.widget.nucleus_connector.extension.NucleusConnectorExtension'>: extension object is still alive, something holds a reference on it. References: ["[0]:type: <class 'method'>, id: 140056081763712"]
[116.152s] [ext: omni.kit.search_core-1.0.5] shutdown
[116.152s] [ext: omni.kit.widget.nucleus_info-1.0.2] shutdown
[116.152s] [ext: omni.kit.window.popup_dialog-2.0.23] shutdown
[116.152s] [ext: omni.ui-2.18.6] shutdown
[116.152s] [ext: omni.kit.renderer.imgui-0.0.0] shutdown
[116.172s] [ext: omni.kit.renderer.capture-0.0.0] shutdown
[116.172s] [ext: omni.kit.renderer.core-0.0.0] shutdown
[116.179s] [ext: omni.kit.renderer.init-0.0.0] shutdown
[116.179s] [ext: omni.appwindow-1.1.5] shutdown
[116.179s] [ext: carb.windowing.plugins-1.0.0] shutdown
[116.180s] [ext: omni.hydra.usdrt_delegate-7.2.39] shutdown
[116.180s] [ext: omni.activity.core-1.0.1] shutdown
[116.181s] [ext: omni.resourcemonitor-105.0.0] shutdown
[116.182s] [ext: omni.hydra.scene_delegate-0.3.2] shutdown
[116.182s] [ext: omni.hydra.rtx-0.1.0] shutdown
[116.191s] [ext: omni.volume-0.4.0] shutdown
[116.191s] [ext: omni.usd.core-1.1.8] shutdown
[116.191s] [ext: omni.usd.schema.omnigraph-1.0.0] shutdown
[116.191s] [ext: omni.kit.exec.core-0.5.0] shutdown
[116.192s] [ext: omni.usd.schema.anim-0.0.0] shutdown
[116.192s] [ext: omni.usd.schema.geospatial-0.0.0] shutdown
[116.192s] [ext: omni.usd.schema.audio-0.0.0] shutdown
[116.192s] [ext: omni.usd.schema.omniscripting-1.0.0] shutdown
[116.192s] [ext: omni.usd.schema.semantics-0.0.0] shutdown
[116.192s] [ext: omni.usd.schema.physics-0.0.0] shutdown
[116.192s] [ext: omni.usd_resolver-1.0.1] shutdown
[116.192s] [ext: omni.usd.libs-1.0.0] shutdown
[116.195s] [ext: omni.gpucompute.plugins-0.0.0] shutdown
[116.195s] [ext: omni.gpu_foundation-0.0.0] shutdown
[116.196s] [ext: omni.graph.exec-0.3.0] shutdown
[116.196s] [ext: omni.mdl.neuraylib-0.2.0] shutdown
[116.196s] [ext: omni.iray.libs-0.0.0] shutdown
[116.196s] [ext: omni.kit.commands-1.4.6] shutdown
[116.197s] [ext: omni.kit.actions.core-1.0.0] shutdown
[116.197s] [ext: omni.kit.clipboard-1.0.3] shutdown
[116.198s] [ext: omni.services.transport.server.http-1.3.0] shutdown
2024-10-06 15:08:13 [116,281ms] [Warning] [omni.ext._impl._internal] omni.services.transport.server.http-1.3.0 -> <class 'omni.services.transport.server.http.server.HTTPServerExtension'>: extension object is still alive, something holds a reference on it. References: ["[0]:type: <class 'frame'>, id: 158262368", "[1]:type: <class 'frame'>, id: 140054972120144", "[2]:type: <class 'frame'>, id: 155659584", "[3]:type: <class 'frame'>, id: 140055071953328"]
[116.310s] [ext: omni.services.transport.server.base-1.1.1] shutdown
[116.311s] [ext: omni.services.core-1.9.0] shutdown
2024-10-06 15:08:13 [116,290ms] [Warning] [omni.ext._impl._internal] omni.services.core-1.9.0 -> <class 'omni.services.core.main.ServicesCoreExtension'>: extension object is still alive, something holds a reference on it. References: ["[0]:type: <class 'method'>, id: 140056066930112"]
[116.319s] [ext: omni.kit.loop-default-0.2.0] shutdown
[116.320s] [ext: omni.kit.telemetry-0.5.0] shutdown
[116.321s] [ext: omni.kit.pip_archive-0.0.0] shutdown
[116.321s] [ext: omni.kit.pipapi-0.0.0] shutdown
[116.321s] [ext: omni.usd.config-1.0.3] shutdown
[116.321s] [ext: omni.mtlx-0.1.0] shutdown
[116.321s] [ext: omni.rtx.shadercache.vulkan-1.0.0] shutdown
[116.321s] [ext: omni.services.facilities.base-1.0.4] shutdown
[116.321s] [ext: omni.stats-0.0.0] shutdown
[116.321s] [ext: omni.timeline-1.0.9] shutdown
[116.321s] [ext: omni.omniverse_renderer_ms.dependencies.pip-0.0.0] shutdown
[116.322s] [ext: omni.client-1.0.1] shutdown
[116.323s] [ext: omni.assets.plugins-0.0.0] shutdown
[116.323s] [ext: omni.kit.async_engine-0.0.0] shutdown
2024-10-06 15:08:13 [116,097ms] [Warning] [carb.assets.plugin] Evicting asset type c1237a43d569db21 v0.1 orphaned snapshot handle 4294967296 (/home/ace/asset/Scenes/Empty Scene/studio_small_09_2k.exr)
... [repeated line showing asset snapshot]
2024-10-06 15:08:15 [118,662ms] [Error] [carb.graphics-vulkan.plugin] pipelineLayouts: 3 or descriptorSetLayouts: 10 is leaking memory. Missing call to destroyResourceBindingSignature()
2024-10-06 15:08:15 [118,907ms] [Warning] [carb] [Plugin: omni.ui] Module /opt/nvidia/omniverse/renderer/extscache/omni.ui-2.18.6+09b309e7.lx64.r.cp310/bin/libomni.ui.so remained loaded after unload request
2024-10-06 15:08:15 [118,910ms] [Warning] [carb] [Plugin: omni.fabric.plugin] Module /opt/nvidia/omniverse/renderer/extscache/omni.usd.libs-1.0.0+09b309e7.lx64.r.cp310/bin/deps/libomni.fabric.plugin.so remained loaded after unload request
2024-10-06 15:08:15 [118,911ms] [Warning] [carb] [Plugin: gpu.foundation.plugin] Module /opt/nvidia/omniverse/renderer/extscache/omni.gpu_foundation-0.0.0+09b309e7.lx64.r.cp310/bin/deps/libgpu.foundation.plugin.so remained loaded after unload request
2024-10-06 15:08:15 [118,916ms] [Warning] [carb] [Plugin: carb.dictionary.plugin] Module /opt/nvidia/omniverse/kit-sdk-launcher/kernel/plugins/libcarb.dictionary.plugin.so remained loaded after unload request
2024-10-06 15:08:15 [118,918ms] [Warning] [omni.core.ITypeFactory] Module /opt/nvidia/omniverse/renderer/extscache/omni.activity.core-1.0.1+09b309e7.lx64.r.cp310/bin/libomni.activity.core.plugin.so remained loaded after unload request.
</pre></code>
some side note, I think this tutorial here skipped the persistent volume mount part in the tutorial.
tokkio
k8s built with ucf_app_builder_cli
For tokkio workflow, I have reinstalled k0s cluster again while making sure that there’s also no port collision (I’ve successfully setup Ingress and deploy my application successfully there so this should validate my claim that k0s actually works). I’ve also created the ngc-api-key-secret
on both default
and ucs-tokkio-audio-video-llm-app
namespace.
Validate that secret exists in `default` namespace
$ k0s kubectl get secrets ngc-api-key-secret -o yaml
apiVersion: v1
data:
NGC_CLI_API_KEY: XXX
kind: Secret
metadata:
annotations:
kubectl.kubernetes.io/last-applied-configuration: |
{"apiVersion":"v1","data":{"NGC_CLI_API_KEY": XXX},"kind":"Secret","metadata":{"annotations":{},"creationTimestamp":null,"name":"ngc-api-key-secret","namespace":"default"}}
creationTimestamp: "2024-10-04T05:51:34Z"
name: ngc-api-key-secret
namespace: default
resourceVersion: "803116"
uid: 7c631613-7836-447e-84ce-876ad7dea8fb
type: Opaque
Validate that secret exists in `ucs-tokkio-audio-video-llm-app` namespace
$ k0s kubectl get secrets ngc-api-key-secret -o yaml -n ucs-tokkio-audio-video-llm-app
apiVersion: v1
data:
NGC_CLI_API_KEY: xxx
kind: Secret
metadata:
annotations:
kubectl.kubernetes.io/last-applied-configuration: |
{"apiVersion":"v1","data":{"NGC_CLI_API_KEY":xxx},"kind":"Secret","metadata":{"annotations":{},"name":"ngc-api-key-secret","namespace":"ucs-tokkio-audio-video-llm-app"}}
creationTimestamp: "2024-10-06T15:48:43Z"
name: ngc-api-key-secret
namespace: ucs-tokkio-audio-video-llm-app
resourceVersion: "1114016"
uid: 2d972c6a-032b-4e3f-8e1c-c5418edaef32
type: Opaque
However, I still can’t build the yaml file with the same error message:
$ ucf_app_builder_cli app build llm-rag/tokkio-llm-app.yaml llm-rag/tokkio-llm-app-params.yaml
2024-10-06 21:46:17,973 - AppBuilder - INFO - Syncing any missing service versions to cache...
2024-10-06 21:46:17,975 - AppBuilder - WARNING - secret 'ngc-api-key-secret' not found in 'animation-graph' (ucf.svc.ia-animation-graph-microservice)
2024-10-06 21:46:17,976 - AppBuilder - WARNING - secret 'ngc-api-key-secret' not found in 'avatar-renderer' (ucf.svc.ia-omniverse-renderer-microservice)
2024-10-06 21:46:18,054 - AppBuilder - INFO - Validating application ...
2024-10-06 21:46:18,088 - AppBuilder - INFO - Building application ucs-tokkio-audio-video-llm-app-4.1.0 ...
Output directory llm-rag/ucs-tokkio-audio-video-llm-app-4.1.0 is not empty. All contents will be removed. Proceed? [y/n]
Output directory llm-rag/ucs-tokkio-audio-video-llm-app-4.1.0 is not empty. All contents will be removed. Proceed? [y/n] y
2024-10-06 21:46:34,512 - AppBuilder - ERROR - Failed to get values from 'https://helm.ngc.nvidia.com/eevaigoeixww/tokkio-4-0/charts/ds-sdr-envoy-0.1.22.tgz' - WARNING: Kubernetes configuration file is group-readable. This is insecure. Location: /var/lib/k0s/pki/admin.conf
Error: failed to fetch https://helm.ngc.nvidia.com/eevaigoeixww/tokkio-4-0/charts/ds-sdr-envoy-0.1.22.tgz : 403 Forbidden
I’m not sure why it doesn’t read the secrets here again.
Hardware and environment
According to @Richard3D mentioned, here’s my details for my hardware and environment:
Operating System: Ubuntu 22.04.4 LTS
GPUs: 8x NVIDIA H100 80GB (4 of them are used to deploy LLMs so only 4 available)
Kubernetes: I’m using k0s for kubernetes
Docker: there’s no docker running
Legacy python: 3.10.12
No modification was done on both build app (llm-rag/tokkio-llm-app.yaml
) and params (llm-rag/tokkio-llm-app-params.yaml
)