RFR: 8321242: Enable WorkerThreads to run tasks in caller thread [v2]

[Axel Boldt-Christmas]

On Tue, 5 Dec 2023 10:24:25 GMT, Aleksey Shipilev <shade at openjdk.org> wrote:

>> `WorkerThreads` is a generic abstraction that allows running the task in multiple threads. There are cases, however, when we only ask for a single thread to carry the computation, and we can accept the caller running the computation instead of ping-ponging with the worker thread. As rendezvous with worker thread is a potential latency hiccup, we would like to avoid delegating work to worker threads unnecessarily. This improves latency on critical paths: the usual round-trip takes about 10..50us on systems I tried.
>> 
>> Nominally, we would like to handle the case for 1 worker requested. But I would argue we would also like to do this even if we are requesting N (N > 1) threads to carry the compute. We can submit (N-1) tasks to workers, and execute the other task in the caller. For lower N-s, this removes additional rendezvous point with workers, and allows caller to complete the bulk of the work while workers are waking up. This would also simplify testing: if caller path is always taken, this would verify the task can indeed be executed by caller.
>> 
>> We cannot, however, do this optimization unconditionally, because the caller thread might not be set up in the same way as workers are, and executing the code in caller might cause bugs. Therefore, it would be nice to have the opt-in option that allows running in caller thread. Since this looks to be the property of the task, I added it to task definition.
>> 
>> This PR is only the infrastructure code additions, without product code behavior changes. New option is sanity-tested by new gtest. Other PRs can then opt-in tasks into this, for example #16882.
>> 
>> Additional testing:
>>  - [x] New gtest
>>  - [x] Linux x86_64 server fastdebug, `tier{1,2,3}`
>>  - [x] Linux AArch64 server fastdebug, `tier{1,2,3}`
>
> Aleksey Shipilev has updated the pull request incrementally with one additional commit since the last revision:
> 
>   More work: gc marks, priorities

>From reading #16882 this seems to come from an effort to reduce code duplication. Specifically the pattern:
```c++ 
  if (can_do_parallel()) {
    workers->run_task(&task, num_workers);
  } else {
    task.work(0);
  }


However I question having this logic be tied to `coordinator_distribute_task`. In all places we see this pattern the `can_do_parallel()` check guards against `workers == nullptr`. This would not go away with this patch. 

Perhaps introduce some `static void WorkerTaskDispatcher::dispatch(WorkerTask* task, WorkerThreads* workers, uint num_workers)` which handles the `workers == nullptr` logic as well (with some assert that the task can run in caller). It would make `coordinator_distribute_task` more clear and clean. Make cleaning up this pattern easier.

Also with regards to the thread priority changing. Currently a lot of places where this "run in caller" pattern occurs in the code today we are running on the VMThread. This threads priority can be changed by the user. Should we change it here, (an potentially even lower its priority).

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

PR Comment: https://git.openjdk.org/jdk/pull/16945#issuecomment-1842436070