@Ori Bandel - Thanks for the question and using MS Q&A platform.
Based on the information you provided, it seems that you are experiencing high CPU usage on your ADX cluster due to heavy calculations. You are considering scaling up (SKU) or scaling out (nodes) to optimize your cluster and reduce the CPU workload.
Scaling up to a stronger or more suitable SKU can help improve the performance of your cluster. However, it may not be the most cost-effective solution. Scaling out by adding more nodes or using auto-scaling can also help distribute the workload and reduce the CPU usage.
In terms of data ingestion, there should not be any risk as long as you follow the best practices for scaling your cluster. It is important to monitor your cluster and adjust the resources as needed to ensure optimal performance.
Before scaling up or out, you may want to consider optimizing your calculations to reduce the workload on your cluster. Additionally, you mentioned that you are using 55%-60% of your cache and considering increasing it from 30 days to 60 days. This can also help improve the performance of your analytics system.
Overall, it is important to find the right balance between performance and cost when optimizing your ADX cluster. You may want to experiment with different configurations and monitor the performance to determine the best solution for your specific needs.
I hope this helps! Let me know if you have any other questions.