RFR: 8348594: Shenandoah: Do not penalize for degeneration when not the fault of triggering heuristic
Kelvin Nilsen
kdnilsen at openjdk.org
Fri Jan 24 18:44:25 UTC 2025
On Fri, 24 Jan 2025 18:18:25 GMT, Kelvin Nilsen <kdnilsen at openjdk.org> wrote:
> Shenandoah heuristics use a penalty mechanism to cause earlier GC triggers when recent concurrent GC cycles degenerate. Degeneration is a stop-the-world remediation that allows GC to catch up when mutator allocations fail during concurrent GC. The fact that we needed to degenerate indicates that we were overly optimistic in delaying the trigger that starts concurrent GC.
>
> We have observed that it is common for degenerated GC cycles to cascade upon each other. The condition that caused an initial degenerated cycle is often not fully resolved by the end of that degenerated cycle. For example, the application may be experiencing a phase change and the GC heuristics are not yet attuned to the new behavior. Furthermore, a degenerated GC may exacerbate the problem condition. During the stop-the-world pause imposed by the first degenerated GC, work continues to accumulate in the form of new client requests that are buffered in network sockets until the end of that degenerated GC.
>
> As originally implemented, each degeneration would "pile on" additional penalties. These penalties cause the GC frequency to continue to increase. And the expanding CPU load of GC makes it increasingly difficult for mutator threads to catchup. The large penalties accumulated while we are trying to resolve the problem linger long after the problem condition has been resolved.
>
> This change does not add further to the degeneration penalties if a new degenerated cycle occurs through no fault of the triggering mechanism. We only add the degeneration penalty if the reason we are now degenerating can be attributed to a consciously late trigger by the heuristic.
[netflix-calibrate-better.xlsx](https://github.com/user-attachments/files/18540298/netflix-calibrate-better.xlsx)
The attached spreadsheet provides a summary of performance benefits of this patch. In the spreadsheet:
Control represents tip without changes
Better Penalty represents https://github.com/openjdk/jdk/pull/23305 (this PR)
Better Progress represents https://github.com/openjdk/jdk/pull/23306
Better Both represents the combined benefits of Better Penalty and Better Progress.
Compared to Control, "Better Both" results are better across all measures:

-------------
PR Comment: https://git.openjdk.org/jdk/pull/23305#issuecomment-2613158108
More information about the hotspot-gc-dev
mailing list