On Tue, 18 Aug 2026 14:45:29 GMT, Maurizio Cimadamore <[email protected]> wrote:
>> Per Minborg has updated the pull request incrementally with one additional >> commit since the last revision: >> >> Address performance regression > > src/java.base/share/classes/java/lang/Thread.java line 301: > >> 299: * Access is confined to this platform thread, directly or as a >> carrier. >> 300: */ >> 301: long[] confinedMemoryPools; > > If we only care about platform threads, maybe a carrier thread local might > also be ok (and leave Thread alone) ? That's a good observation and a clear alternative. Going forward, it is likely the FFM API will be used more and more, which would push us in the direction of using an array directly on Thread. On workloads with no FFM use (and no use within the JDK), a carrier thread local would be better. ------------- PR Review Comment: https://git.openjdk.org/jdk/pull/31365#discussion_r3812429118
