I have a job with strict performance requirements running in Azure Databricks. I had configured pools to reduce the startup time - but of late I'm seeing that the job cluster startup time is in the order of 5 to 8 minutes
If you are using pools then you should consider keeping a min idle count of machines greater than 2. This will allow you to have machines available and ready to use. If you have 0 machines on idle then the first job executed against the pool will have to wait for the machines to become available.
