Azure Proactive Resiliency Library v2
Tools Glossary GitHub GitHub Issues Toggle Dark/Light/Auto mode Toggle Dark/Light/Auto mode Toggle Dark/Light/Auto mode Back to homepage

accounts

Summary

RecommendationImpactCategoryAutomation AvailableIn Azure Advisor
Ensure AOAI models are deployed using Global deploymentHighHigh AvailabilityNoNo
Deploy a PAYG instance of the model with provisioned throughput to manage overflow effectivelyHighHigh AvailabilityNoNo
Ensure that models are deployed using Global batch for large scale processingHighScalabilityNoNo
Ensure AOAI models are deployed using Data Zone Standard for data residency requirementsHighGovernanceNoNo
Deploy AOAI Service in multiple regions using Standard and/or Provisioned deploymentsHighHigh AvailabilityNoNo

Details


Ensure AOAI models are deployed using Global deployment

Impact:  High Category:  High Availability

APRL GUID:  081fc8a4-b2d9-405b-b351-334e621016f5

Description:

Global deployments leverage Azure's global infrastructure to route customer traffic to the best available data center for the customer’s inference requests. This ensures highest initial throughput limits and best model availability while still providing our uptime SLA and low latency.

Potential Benefits:

Low latency, best model availability, business continuity
Learn More:
Learn More

ARG Query:

Click the Azure Resource Graph tab to view the query

// cannot-be-validated-with-arg


Deploy a PAYG instance of the model with provisioned throughput to manage overflow effectively

Impact:  High Category:  High Availability

APRL GUID:  0c193899-da60-4a52-b4a0-77d75ac8c5c5

Description:

Provisioned Throughput offers pre-allocated capacity for consistent workloads, while Pay-as-You-Go charges for actual usage, ideal for variable workloads. During overflow, the Pay-as-You-Go instance manages excess load, ensuring service efficiency

Potential Benefits:

PAYG model balances cost and performance and helps scale
Learn More:
Learn More

ARG Query:

Click the Azure Resource Graph tab to view the query

// cannot-be-validated-with-arg


Ensure that models are deployed using Global batch for large scale processing

Impact:  High Category:  Scalability

APRL GUID:  8aa9744b-f302-4b05-9776-51d6dd3d0c3a

Description:

Global batch efficiently handles large-scale tasks within 24 hours. Submit requests in a single file, with a separate quota to protect online workloads. Key uses: data processing, content generation, document review, customer support automation, data extraction, NLP tasks, and marketing

Potential Benefits:

Cost effective faster turnaround for large-scale processing.
Learn More:
Learn More

ARG Query:

Click the Azure Resource Graph tab to view the query

// cannot-be-validated-with-arg


Ensure AOAI models are deployed using Data Zone Standard for data residency requirements

Impact:  High Category:  Governance

APRL GUID:  ac3add17-013e-41a5-af91-9fefce794a00

Description:

Data zone deployments route customer traffic to the highest availability data center within the defined data zone, ensuring data at rest remains within the Azure OpenAI resource geography. This approach offers increased quota limits and ensures data processing occurs within the specified data zone

Potential Benefits:

Enforce data residency and compliance standards
Learn More:
Learn More

ARG Query:

Click the Azure Resource Graph tab to view the query

// cannot-be-validated-with-arg


Deploy AOAI Service in multiple regions using Standard and/or Provisioned deployments

Impact:  High Category:  High Availability

APRL GUID:  61187af4-7d36-4b48-b16e-de78bef143a0

Description:

If your service needs to always be available, design AOAI Service to either failover into another region or split the workload between two or more regions. Applications requiring high degrees of resiliency should consider this to strengthen their model infrastructure.

Potential Benefits:

Ensures business continuity during regional outages.
Learn More:
Learn More

ARG Query:

Click the Azure Resource Graph tab to view the query

// cannot-be-validated-with-arg