RFR: 8319876: Reduce memory consumption of VM_ThreadDump::doit [v3]

[Long Yang]

On Mon, 13 Nov 2023 10:11:26 GMT, Long Yang <duke at openjdk.org> wrote:

>> I would like to fix this.
>> 
>> Create 4096 threads, and the stack depth of each thread is 256. 
>> After running jmx.dumpAllThreads(true, true), the RSS reaches 5.3GiB. 
>> After optimization, the RSS is 250MiB.
>> 
>> I would appreciate it if anyone could review this.
>> 
>> ---------
>> update
>> 
>> If the number of `threads` and `stack depth` are relatively large, we need to apply for more space in `ResourceArea` during the execution of `jmx.dumpAllThreads(true, true)`.
>> 
>> The reason is that `VM_ThreadDump::doit` creates `vframe` for each `frame` of each `thread`.
>> https://github.com/openjdk/jdk/blob/fe0ccdf5f8a5559a608d2e2cd2b6aecbe245c5ec/src/hotspot/share/services/threadService.cpp#L704
>> sizeof `vframe` is 4808 (bytes), and sizeof `compiledVFrame` is 4824 (bytes), mainly because the `xmm registers` in `RegisterMap` are relatively large. Assuming there are 4096 `threads` and each `thread` has 256 `frames`, the memory required is 4096 * 256 * 4824 = 4.7GiB。
>> 
>> These memories of all threads are released once by the the initial `ResourceMark` of `VM_ThreadDump::doit`.
>> https://github.com/openjdk/jdk/blob/fe0ccdf5f8a5559a608d2e2cd2b6aecbe245c5ec/src/hotspot/share/runtime/vmOperations.cpp#L269
>> My solution is to add a `ResourceMark` for each thread.
>
> Long Yang has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Use VMThread::vm_thread() to avoid the need to call Thread::current()

Could I get another review ?

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

PR Comment: https://git.openjdk.org/jdk/pull/16598#issuecomment-1815842813