RFR: 6203: Add ZGC allocation stall rule

[Marcus Hirt]

On Wed, 9 Jul 2025 14:17:10 GMT, Suchita Chaturvedi <schaturvedi at openjdk.org> wrote:

> This enhancement is to add new rule for ZGC Allocation Stall events.
> 
> The default configuration:
>  
> <img width="946" alt="image" src="https://github.com/user-attachments/assets/0d39ae26-fdc4-49e3-a0ed-fb7f7da8f709" />
> 
> Here are few screenshots for reference:
> 
> <img width="344" alt="image" src="https://github.com/user-attachments/assets/e7efe1e2-d6b3-4a05-8ea6-1bf2e8b8c15f" />
> 
> <img width="353" alt="image" src="https://github.com/user-attachments/assets/a3d3862f-96d2-4292-947f-4562c7f9f3d3" />
> 
> <img width="344" alt="image" src="https://github.com/user-attachments/assets/9616eea6-bce8-4395-a846-db343fe349f2" />
> 
> <img width="341" alt="image" src="https://github.com/user-attachments/assets/376a100e-ac05-48fe-a9c3-754923c3d79e" />
> 
> <img width="353" alt="image" src="https://github.com/user-attachments/assets/cfa7c5f1-08f0-44b4-a49d-28504439a631" />
> 
> Ignored
> 
> <img width="352" alt="image" src="https://github.com/user-attachments/assets/3c00c22e-e64d-46b0-8b64-ed653ed1fc4b" />
> 
> If we change default configuration as below:
> 
> <img width="367" alt="image" src="https://github.com/user-attachments/assets/8da64985-8446-44b8-bfb4-696a726b5255" />
> 
> <img width="350" alt="image" src="https://github.com/user-attachments/assets/ad89f02e-39b4-4df4-aae7-43cec9cc9a91" />
> 
> <img width="347" alt="image" src="https://github.com/user-attachments/assets/b3ec1081-26dd-4391-9e0f-0b4c64a7e3c1" />
> 
> <img width="344" alt="image" src="https://github.com/user-attachments/assets/106a7c3e-aaaf-495a-8c6f-281c96371e6e" />

As per the JMC dev slack, perhaps sum of stalled time per minute could be a good one? That one would have to be a rate to be recording length independent. Perhaps also combined with a higher score if very long individual allocation stalls are present?

I also opened https://bugs.openjdk.org/browse/JDK-8362416 to make the rule more useful in case there are a lot of stalls under the default 10ms threshold of the current ZGC Allocation Stall event. We shouldn't block this PR on that work though, but rather ensure we use the new event when available. I will open a new JMC issue to track this.

-------------

PR Comment: https://git.openjdk.org/jmc/pull/664#issuecomment-3078363462