Help Center/ ModelArts/ Model Inference/ Deploying an AI Application as a Service/ Upgrading a Service
Updated on 2023-10-16 GMT+08:00
View PDF
Share

Upgrading a Service

For a deployed service, you can modify its basic information to match service changes and change the AI application version to upgrade it.

You can modify the basic information about a service in either of the following ways:

Method 1: Modify Service Information on the Service Management Page

Method 2: Modify Service Information on the Service Details Page

Prerequisites

The service has been deployed. The service in the Deploying state cannot be upgraded by modifying the service information.

Constraints

  • Improper upgrade operations will interrupt service running during the upgrade. Therefore, exercise caution when performing this operation.
  • ModelArts supports hitless rolling upgrade of real-time services in some scenarios. Before upgrade, prepare for it and confirm the prerequisites.
    Table 1 Scenarios for hitless rolling upgrade

    Meta Model Source for Creating an AI Application

    Using a Public Resource Pool

    Using a Dedicated Resource Pool

    Training job

    Not supported

    Not supported

    Template

    Not supported

    Not supported

    Container image

    Not supported

    Supported. The custom image for creating an AI application must meet Custom Image Specifications for Creating AI Applications.

    OBS

    Not supported

    Not supported

Method 1: Modify Service Information on the Service Management Page

  1. Log in to the ModelArts management console and choose Service Deployment from the left navigation pane. Go to the service management page of the target service.
  2. In the service list, click Modify in the Operation column of the target service, modify basic service information, and submit the modification task as prompted.

    When some parameters are modified, the system automatically restarts the service for the modification to take effect. When you submit a service modification task, if a restart is required, a dialog box will be displayed.

    • For details about the real-time service parameters, see Deploying as a Real-Time Service. To modify a real-time service, you also need to set Max. Invalid Instances to set the maximum number of nodes that can be concurrently upgraded, during which time these nodes are invalid.
    • For details about the batch service parameters, see Deploying as a Batch Service.

Method 2: Modify Service Information on the Service Details Page

  1. Log in to the ModelArts management console and choose Service Deployment from the left navigation pane. Go to the service management page of the target service.
  2. Click the name of the target service. The service details page is displayed.
  3. Click Modify in the upper right corner of the page, modify the service details, and submit the modification task as prompted.

    When some parameters are modified, the system automatically restarts the service for the modification to take effect. When you submit a service modification task, if a restart is required, a dialog box will be displayed.

    • For details about the real-time service parameters, see Deploying as a Real-Time Service. To modify a real-time service, you also need to set Max. Invalid Instances to set the maximum number of nodes that can be concurrently upgraded, during which time these nodes are invalid.
    • For details about the batch service parameters, see Deploying as a Batch Service.