RFR: 8322630: Remove ICStubs and related safepoints

[Erik Österlund]

On Tue, 23 Jan 2024 14:47:49 GMT, Thomas Schatzl <tschatzl at openjdk.org> wrote:

> Fwiw, the change makes class unloading regress significantly in a class unloading stress test (unloading 60k classes), seemingly tripling the time it takes for the "Purge Unlinked NMethods" phase (~20ms -> ~60ms).
> 
> This may not be a problem for the concurrent gcs, but can be for the STW ones.
> 
> (Overall max G1 remark pause times went from 160ms to 220ms, regular Remark pauses which do class unloading from 120ms to 160ms).

If the level of ~1 ms per 1000 unloaded classes worth of latency issue is crucial for G1, then maybe it's time for G1 to at least run purging concurrently?

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

PR Comment: https://git.openjdk.org/jdk/pull/17495#issuecomment-1906338815