On Tue, 21 Jan 2025 23:48:14 GMT, Vladimir Ivanov <vaiva...@openjdk.org> wrote:
>> The synchronized scope was reduced from whole methods to sections that need >> hash map access control. The tier1 and jaxp tests are OK. The score of the >> specjvm2008:xml.transform improved a little bit. On the Xeon 8480+ reported >> scores are: >> original: 1vCPU - 148.4, 112vCPU - 12743.4, 224vCPU - 13481.31 ops/m >> patched: 1vCPU - 149.77, 112vCPU - 13122.82, 224vCPU - 14751.57 ops/m >> >> According to the JFR the locking time for XMLReader object reduced from >> ~27sec to ~20sec for 224vCPU run. > > Vladimir Ivanov has updated the pull request incrementally with one > additional commit since the last revision: > > 8346230 [perf] scalability issue for the specjvm2008::xml.transform workload Thanks for your comment. You are correct. The 'volatile' modifier does not need here. Also it can't be 'final' while may be updated during runs. The thread local variable is OK here. Tier1 and jaxp tests are OK. Scores are same. ------------- PR Comment: https://git.openjdk.org/jdk/pull/23185#issuecomment-2606007098
