RFR: 8348402: PerfDataManager stalls shutdown for 1ms [v3]

[Aleksey Shipilev]

On Fri, 31 Jan 2025 04:37:15 GMT, David Holmes <dholmes at openjdk.org> wrote:

>> Aleksey Shipilev 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 six additional commits since the last revision:
>> 
>>  - Merge branch 'master' into JDK-8348402-perfdatamanager-stall
>>  - Also add a blurb in usage doc
>>  - Only protect one dodgy place
>>  - Merge branch 'master' into JDK-8348402-perfdatamanager-stall
>>  - Fix minimal build
>>  - Use GlobalCounter to coordinate deletions
>
> src/hotspot/share/runtime/objectMonitor.hpp line 214:
> 
>> 212:   // Only perform a PerfData operation if the PerfData object has been
>> 213:   // allocated and if the PerfDataManager has not freed the PerfData
>> 214:   // objects which can happen at normal VM shutdown. Additionally, we
> 
> This commentary also applies to the OM_PERFDATA_OP case. But we can also say to use that form when not safepoint-safe, and the below when safepoint-safe.

Right. See if got a good level of guidance in the comments now?

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

PR Review Comment: https://git.openjdk.org/jdk/pull/23293#discussion_r1936853107