Optimize thread state handling in function call code

[jdemeyer]

BPO	36616
Nosy	@vstinner, @encukou, @markshannon, @jdemeyer
PRs	bpo-36616: optimize handling of thread state in function call code #12839

^{Note: these values reflect the state of the issue at the time it was migrated and might not reflect the current state.}

Show more details

GitHub fields:

assignee = None
closed_at = <Date 2019-04-16.13:12:18.842>
created_at = <Date 2019-04-12.16:25:26.209>
labels = ['interpreter-core', 'invalid', '3.8', '3.9', 'performance']
title = 'Optimize thread state handling in function call code'
updated_at = <Date 2019-04-24.16:28:20.847>
user = 'https://github.com/jdemeyer'

bugs.python.org fields:

activity = <Date 2019-04-24.16:28:20.847>
actor = 'vstinner'
assignee = 'none'
closed = True
closed_date = <Date 2019-04-16.13:12:18.842>
closer = 'vstinner'
components = ['Interpreter Core']
creation = <Date 2019-04-12.16:25:26.209>
creator = 'jdemeyer'
dependencies = []
files = []
hgrepos = []
issue_num = 36616
keywords = ['patch']
message_count = 8.0
messages = ['340078', '340161', '340242', '340243', '340270', '340290', '340341', '340790']
nosy_count = 4.0
nosy_names = ['vstinner', 'petr.viktorin', 'Mark.Shannon', 'jdemeyer']
pr_nums = ['12839']
priority = 'normal'
resolution = 'not a bug'
stage = 'resolved'
status = 'closed'
superseder = None
type = 'performance'
url = 'https://bugs.python.org/issue36616'
versions = ['Python 3.8', 'Python 3.9']

[jdemeyer]

The bytecode interpreter uses an inline function call_function() to handle most function calls. To check for profiling, call_function() needs to call to PyThreadState_GET().

In the reference implementation of PEP-590, I saw that we can remove these PyThreadState_GET() calls by passing the thread state from the main eval loop to call_function().

I suggest to apply this optimization now, because they make sense independently of PEP-580 and PEP-590 and to give a better baseline for performance comparisons.

[jdemeyer]

Mark, Petr, do you agree? I like the way how the reference implementation of PEP-590 improves the handling of profiling. However, that change really has little to do with PEP-590, it's something that we can do independently.

[encukou]

Indeed, this is a good idea.

[vstinner]

I wanted to do that, but I never measured the overhead of PyThreadState_GET() calls. Subtle detail: using _PyThreadState_GET() ("_Py") prefix rather than PyThreadState_GET() ensures that you get the optimized macro ;-)

[jdemeyer]

The gain is small, but it's there.

I made some further changes:

• replacing code of the form

    sp = stack_pointer;
    call_function(..., &sp, ...)
    stack_pointer = sp;

by

    call_function(..., &stack_pointer, ...)

• fold the inline function do_call_core() in the main eval loop (the function became so small that there was no longer a reason to pull it out of the main loop)

• removed pointless check PyMethod_GET_SELF(func) != NULL (methods always have self != NULL)

[vstinner]

The gain is small, but it's there.

Do you mean a performance speedup? If yes, can you please run a micro-benchmark?

[vstinner]

Jeroen Demeyer closed his PR 12839, so I close the issue as well.

[vstinner]

See also my PR 12934 which includes a similar change but for correctness, not for optimization.