IEC Type 3: Android cloud native applications on Arm servers in edge for Integrated Edge Cloud (IEC) Blueprint Family

IEC Type 3: Android cloud native applications on Arm servers in edge for Integrated Edge Cloud (IEC) Blueprint Family

Use Case Details:

Attributes

Description

Informational

Type

New

 

Industry Sector

Telco, Cloud 

 

Business driver

  • Edge cloud requires initiatives for cloud gaming on Android platform  

  • 5G + edge bring low latency and high-throughput for cloud gaming, which improves user experience

  • More and more Android applications will migrate into edge compute platform. Building an android platform is necessary, and it's rigid demand. 

 

Business use cases

  Android Cloud Gaming

 

Business Cost - Initial Build Cost Target Objective

Using virtualization technology instead of mobile chip board on ARM server will reduce the cost of android platform.  ARM server board also let android platform more flexible and more agile.

In order to support cloud gaming and AR/VR, ARM server need have GPU inside. 

  • 2 ARM Nodes

  • Android 9.0

    • GPU (AMD, NVIDIA)

  • Android virtualization layer: Robox, docker.

 

Business Cost – Target Operational Objective

It more like a cloud platform, but it's specific for android application.  

  • It needs Helm and Ansible for the automation and management tools to keep operational cost lower

  • It needs to monitor the status of android system status and application status. 

  • Maintain a mixed edge platform including x86 and ARM. It's more complex

  • Kubernetes

  • Android 9.0

    • GPU (AMD, NVIDIA)

  • Host OS kernel optimization;

  • Android virtualization layer: Robox, docker.

  • GPU (AMD/NVIDIA)

  • Both ARM and X86 can support it.

 

Security need

Security is very important in this use case, especially for containerized android system. 

 

Regulations

N/A

 

Other restrictions

N/A

 

Additional details

N/A

 

 

Case Attributes

Description

Informational

Type

New

 

Blueprint Family - Proposed   Name

Integrated Edge Cloud (IEC)

 

Use Case

Cloud Gaming and AR/VR

 

Blueprint proposed Name

IEC Type 3: Android cloud native applications on Arm servers in edge

 

Initial POD Cost (capex)

2 ARM bare metal machines, 1 10G switch, 1 AMD GPU, 1 NIVIDA GPU

 

Scale & Type

For the smallest deployment, this requires 2 ARM bare metal machines. For large deployments, this could span to large number of bare metal machines.

 

Applications

Android application, such as cloud gaming, VR/AR.

 

Power Restrictions

N/A

 

Infrastructure orchestration

Host:

  • Bare Metal Provisioning:Ansible

  • OS: Ubuntu

  • GPU Driver: AMD,NVIDIA:

  • Network: OVS 

  • Android virtualization layer: Robox container

  • Host OS kernel optimization

Guest OS Andriod: 

  • GPU Driver (AMD, NVIDIA)

 

SDN

N/A

 

Workload Type

  • Android applications 

 

Additional Details

N/A

 

 

Blueprint was approved by the TSC on 2 Apr 2020.

Election ended on 22 April 2020- Hanyu Ding was the winner

 

Committer

Committer

Company

 Committer Contact Info

Committer Bio

Committer Picture

PTL

Yongsu Zhang

ByteDance

zhangyongsu@bytedance.com

 

 

 

Kairui She

ByteDance

shekairui@bytedance.com

 

 

 

Shi Lei

China Mobile

shileiyj@chinamobile.com

 

 

 

@Trevor Tao (Deactivated)

Arm

trevor.tao@arm.com

 

 

 

@Jingzhao Ni (Arm Technology China) (Deactivated)

Arm

jingzhao.ni@arm.com

 

 

 

@Jianlin Lv (Arm Technology China) (Deactivated)

Arm

jianlin.lv@arm.com

 

 

 

Hanyu Ding

China Mobile

dinghanyu@chinamobile.com

 

 

Apr 22, 2020 to Apr 22, 2021 

Wales Wang WeiXun

Mobile Intelligence Cloud Co.

waleswang@runtronic.com

 

 

 

@Ming Li

NVIDIA

mingl@nvidia.com

 

 

 

zhaoruizhe

bytedance

zhaoruizhe@bytedance.com

 

 

 

Yanjun Chen

China Mobile

chenyanjunyjy@chinamobile.com

 

 

 

 @Tide Wang

Phytium

wanghailong@phytium.com.cn

 

 

 

@Davy Zhang

Y-Semi

davy.zhang@ysemi.cn

 

 

 

 

 

 

 

 

 

 

Contributor

Contributor

Company

 Contributor Contact Info

Contributor Bio

Contributor Picture

Corey Ji

Y-Semi Computing

corey.ji@ysemi.cn

 

 

Weiwei Wang

YLCloud

www@you-cloud.cn

 

 

 

As per the Akraino Community process and directed by TSC, a blueprint which has only one nominee for Project Technical Lead (PTL) will be the elected lead once at least one committer seconds the nomination after the close of nominations.  If there are two or more, an election will take place.

 

 

TS2280v1

TS2280v2

 

TS2280v1

TS2280v2

CPU

2x 32 core 2.4 GHz Hi1616 Processors

2x 32 core 2.6 GHz Hi1620 Processors

RAM

8x 16GB RDIMM-Tx2 

8x 16GB DDR4-DIMM

Storage

2x 1TB SSD

2x 1TB SSD

Networking

2x 1/10Gbe BASE-T (1 connected)
1x IPMI  Lights-out Management

2x 1/10Gbe SFP+ (connected)

1x IPMI / Lights-out Management

GPU

1 AMD GPU ,1 NVidia GPU

 

Servers and Switches

Server Name

IPMI Address

Public Network Address

Switch Port(s)

OS Installed

93

10.x

10.x

gigabyte-edgecore2: left 40Bbe Port 1, right 40Gbe Port 2, left 10Gbe Port 7 Breakout 1,  right 10Gbe Port 7 Breakout 2

Ubuntu 18.04

174

10.x

10.x

gigabyte-edgecore2: left 40Bbe Port 3, right 40Gbe Port 4, left 10Gbe Port 7 Breakout 3, right 10Gbe Port 7 Breakout 4

Ubuntu 18.04

 

BP: