how max_retry_interval_millis works with retry_on_timeout in Data bricks.

[Pratibha]

my project I want if job take longer time then it will terminate and again it will try even if there is timeout error and in databricks launched status should show retry by scheduler and it should follow min_retry_interval_millis before  start retry run.. how I can do this. I have set all parameter in config but once job gone in timeout it immediately start running and luanched status is not changing means it is not indicating my job is retried. please help

[Kaniz_Fatma]

Hi @Pratibha, Configure a Timeout for a Task: You can set a maximum completion time for a task in the Timeout field. 

If the task is incomplete within this time, Databricks sets its status to "Timed Out".

Configure a Retry Policy for a Task: You can configure a policy determining when and how often faile....

Use the Jobs API: If you’re using the Jobs API and encounter a 500-level error, Databricks recommend....

Please note that the job status might not change immediately in the Databricks UI. The status might take some time to update and reflect the retry.

Suppose you’ve configured these settings, and the job is still not retrying as expected. In that case, double-checking your configuration settings might be a good idea. Please remember to never hard code secrets or store them in plain text. Use the Secrets API to manage secrets in the Databricks CLI.

Use the Secrets API to manage secrets in the Databricks CLI.

I hope this helps! Let me know if you have any other questions. 😊

[Kaniz_Fatma]

Thank you for posting your question in our community! We are happy to assist you.

To help us provide you with the most accurate information, could you please take a moment to review the responses and select the one that best answers your question?

This will also help other community members who may have similar questions in the future. Thank you for your participation and let us know if you need any further assistance!