Potential performance regression with Python 3.14 bench_mp_pool on Linux

[NoAnyLove]

Bug report

Bug description:

Hi team, I was running pyperformance and found that the bench_mp_pool in 3.14 was way more slower than in 3.13.

I uses pyperformance-1.11.0 installed from master branch and conda-forge Python builds, the system is Ubuntu 22.04.

+-------------------+-----------------------------+-----------------------------+
| Benchmark         | Python 3.13.7               | Python 3.14.0               |
+===================+=============================+=============================+
| bench_mp_pool     | 6.08 ms                     | 1.91 sec: 315.05x slower    |
+-------------------+-----------------------------+-----------------------------+

I also tried it on another Ubuntu 22.04 box, it was better but still tens of times slower,

+-------------------+-----------------------------+-----------------------------+
| Benchmark         | Python 3.13.7               | pPython 3.14.0              |
+===================+=============================+=============================+
| bench_mp_pool     | 13.4 ms                     | 367 ms: 27.42x slower       |
+-------------------+-----------------------------+-----------------------------+

CPython versions tested on:

3.14

Operating systems tested on:

Linux

[LamentXU123]

According to speed-python timeline here. We don't see that much drop of performance on bench_mp_pool on the main branch:

So I'm not that sure about if this could be reproduced.

[picnixz]

Maybe it's because we are changing the default start method? we switched from fork to forkserver on Linux in Python 3.14. Could you try to alter the benchmark and explicitly call multiprocessing.set_start_method("fork") to see what happens? (I don't know where you should put that call though...)

We don't see that much drop of performance on bench_mp_pool on the main branch:

@LamentXU123 That's not a comparison between 3.14 and 3.13.

[NoAnyLove]

@picnixz I think you're right, 3.14 matches 3.13 after adding multiprocessing.set_start_method("fork").

btw, I'm running benchmarks on a small Ubuntu VM with a few cores, 3.14 is only a few times slower than 3.13.

Without multiprocessing.set_start_method("fork"),

+-------------------+---------+-----------------------+
| Benchmark         | py313   | py314                 |
+===================+=========+=======================+
| bench_mp_pool     | 15.6 ms | 43.1 ms: 2.77x slower |
+-------------------+---------+-----------------------+

With multiprocessing.set_start_method("fork"),

+-------------------+------------+-----------------------+
| Benchmark         | py313_fork | py314_fork            |
+===================+============+=======================+
| bench_mp_pool     | 16.6 ms    | 16.3 ms: 1.02x faster |
+-------------------+------------+-----------------------+

[thesamesam]

Two issues w/ forkserver, but it may be distinct from these:

• multiprocessing forkserver main contains dead main_path= handling code #126631 preloading '__main__' with forkserver has been broken for a long time #98552 (gh-126631: fix pre-loading of __main__ #135295)
• forkserver not reused in child processes #86354 (gh-86354: Fix child processes not reusing forkserver created by parent #139537)

[picnixz]

@gpshead Was such slowdown actually planned or is it a legitimate issue somewhere?