Skip to content
This repository was archived by the owner on Nov 11, 2024. It is now read-only.

Deploy on Xeon E3 with Gen GFX using Kubernetes

Coco edited this page Jun 6, 2019 · 12 revisions

Kubernetes Deployment on E3

Enable Intel GPU for k8s

Verify kubelet socket exists in /var/lib/kubelet/device-plugins/ directory

$ ls /var/lib/kubelet/device-plugins/kubelet.sock
/var/lib/kubelet/device-plugins/kubelet.sock

Build and run intel gpu plugin

$ script/enable_gpu_plugin.sh
$ /usr/local/go/src/github.com/intel/intel-device-plugins-for-kubernetes/cmd/gpu_plugin/gpu_plugin
GPU device plugin started
Start server for i915 at: /var/lib/kubelet/device-plugins/gpu.intel.com-i915.sock
Device plugin for i915 registered

Verify GPU device plugin is registered

$ kubectl describe node | grep gpu.intel.com
gpu.intel.com/i915:  1
gpu.intel.com/i915:  1
 gpu.intel.com/i915  0          0

Start CDN transcode service

$ cd build
$ make start_kubernetes

Playback

Web browser playback

Visit https://:30443/ using any web browser, you will see the playlist and then click any of the streams in the playlist to playback.

VLC playback

You can also use Windows VLC player to playback the HTTPs streams provided by the sample service. please run below commands. vlc https://:30443/hls/big_buck_bunny_1280x720/index.m3u8

Clone this wiki locally