RFR: 8322732: ForkJoinPool may underutilize cores in async mode [v7]
Viktor Klang
vklang at openjdk.org
Wed May 29 14:19:06 UTC 2024
On Wed, 29 May 2024 11:33:40 GMT, Doug Lea <dl at openjdk.org> wrote:
>> This set of changes address causes of poor utilization with small numbers of cores due to overly aggressive contention avoidance. A number of further adjustments were needed to still avoid most contention effects in deployments with large numbers of cores
>
> Doug Lea has updated the pull request with a new target base due to a merge or a rebase. The incremental webrev excludes the unrelated changes brought in by the merge/rebase. The pull request contains 41 additional commits since the last revision:
>
> - Merge branch 'openjdk:master' into JDK-8322732
> - Add test for utilization with interdependent tasks
> - Un-misplace onSpinWait call
> - Adjust control flow
> - Reduce memory stalls
> - Merge branch 'openjdk:master' into JDK-8322732
> - More performance tradoffs
> - Address review comments
> - Merge branch 'openjdk:master' into JDK-8322732
> - Repack some fields; adjust control flow
> - ... and 31 more: https://git.openjdk.org/jdk/compare/3d109313...cf5fe55c
src/java.base/share/classes/java/util/concurrent/ForkJoinPool.java line 2061:
> 2059: w.stackPred = (int)pc; // set ctl stack link
> 2060: qc = (active & LMASK) | ((pc - RC_UNIT) & UMASK);
> 2061: if (pc == (pc = compareAndExchangeCtl(pc, qc)))
If I'm reading this right you might want to add a comment :)
Suggestion:
if (pc == (pc = compareAndExchangeCtl(pc, qc))) // consistent
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/19131#discussion_r1618974704
More information about the core-libs-dev
mailing list