Table of Contents |
---|
...
The document provides guidance to install the ote-stack platform on AI Edge Blueprint, which covers the information of hardware requirement, prerequisite software and the detailed step. The ote-stack platform can be installed on Kubernetes or on a system with Docker support. The IEC cluster, which is based on Kubernetes, is chosen to be the edge infrastructure for AI Edge. The installation guide of IEC R2 can be got in here.
The guide shows step by step to deploy ote-stack platform with one edge cluster as well as add a new edge cluster to management.
License
Apache 2.0 license
How to use this document
The guide covers the details of pre-installation requirements, installation steps and uninstallation guide. The installation steps should be executed before the prerequisites and pre-installation requirements are ready. In addition, one IEC edge cluster with 3 nodes needs to be prepared in advance.
...
View file | ||||
---|---|---|---|---|
|
Software Prerequisites
- Available harbor (>=1.7, <2.0) with admin user and password
- At least one IEC edge cluster with healthy container network.
...
A mysql database is required to store to store the related metadata of OTE models, like users, businesses, projects, apps, deployments, clusters, nodes, etc. The database `sys When the OTE runs, the OpenAPI Server will connect to the database "sys_ote_manage_platform` is consists of following tablesplatform" for providing services. Some brief description of tables which related to this database are shown below:
- tb_system_config stores global configuration of OTE web portal.
- tb_business_info maintains the relation between the users of OTE users and the namespace which divide cluster resources between different users.
- tb_ote_web_users stores the informations of general users and administrator in OTE stack.
- tb_ote_web_repository_users stores the information of users who are used to pull of harbor server for pulling docker images when applications are being deployed.
- tb_ote_cluster_label stores the labels which are attached to edge clusters, while the information of clusters are stored as CRD resource in the etcd.
- tb_ote_node_label stores the labels which are attached to edge nodes, while the information of edge nodes are stored as CRD resource in the etcd.
- tb_app_info stores the information about application that will be deployed, such as name, image, required resource, execution command.
- tb_deploy_info maintains the information and status of deployment deployments related to the application that stored in tb_app_info.
- tb_alert_info displays alert messages sent by alertmanager server.
Following the installation steps below, a new mysql database container, which contains the configuration and db tables of OTE, will be deployed to the edge cluster. If you need to store the these OTE metadata in your own database, you can execute the following schema script to create the database and the related tables.
...
Clone the AIEdge git repo and edit the configuration file (interface_conf) by setting:
- hostname of the node _name in edge cluster which would deploy that the ote-stack platform will be deployed to
- docker repository for pulling images of ote-stack components
- informations of harbor repository such as admin password and domain
Code Block |
---|
git clone https://gerrit.akraino.org/r/aiedge.git cd aiedge git submodule init git submodule update cd ote-stack/aiedge/deployments vim interface_conf |
...
Please refer the section "Pre-Installation Requirements" in wiki IEC Type1&2 Installation Guide for R2 and make sure the environment requirements met.
...
Please prepare three arm servers and build a edge cluster according to wiki IEC Type1&2 Installation Guide for R2.
Including Upstream Patches with Deployment
...
- Apache License 2.0: https://www.apache.org/licenses/LICENSE-2.0
- AI Edge Wiki: Video Security Monitoring Release 3 Documentation