gh-113141: Mimallocv3 by DinoV · Pull Request #159718 · python/cpython · GitHub

Issue: Mimalloc differences from upstream #113141

The following commit authors need to sign the Contributor License Agreement:

daanl@outlook.com

Documentation build overview

📚 cpython-previews | 🛠️ Build #35286120 | 📁 Comparing a36efb6 against main (415ebff)

🔍 Preview build

19 files changed · ± 19 modified

± Modified

@daanx can you please sign the CLA?

@daanx can you please sign the CLA?

Ah yes, but not really for the current PR as that includes the full mimalloc v3 vendored sources and that is a separate project under the MIT license.

I can of course sign off for the changes I made on the CPython side. The current PR contains both, maybe we can split it? I think commit cedd47b is the CPython part only, while the other commits are just importing mimalloc v3 as a vendored library.

Using MI_WIN_INIT_USE_FLS is not really encouraged for mimalloc. If we can use the default that would be best.

This reverts commit fbe3cfe.

Using MI_WIN_INIT_USE_FLS is not really encouraged for mimalloc. If we can use the default that would be best.

There's a crash on the Windows builds w/o it currently (and it seems to show up basically at startup but the freeze programs make it through it). I was planning on digging into it more later but this is what Claude came up as a fix - I just don't have immediate access to a Windows machine to see where the actual crash is coming from. But that's why it's there for now.

Right now I'm just trying to get things to green CI and then I'll clean up the final result.

@corona10 Hey here it is!

For TSAN fail see: 2599016

IIRC, it was already happened at

cpython/Objects/mimalloc/os.c

Lines 245 to 268 in 34fe59b

    
           else { 
        
             // if not aligned, free it, overallocate, and unmap around it 
        
             // NOTE(sgross): this warning causes issues in Python tests 
        
             // _mi_warning_message("unable to allocate aligned OS memory directly, fall back to over-allocation (size: 0x%zx bytes, address: %p, alignment: 0x%zx, commit: %d)\n", size, p, alignment, commit); 
        
             mi_os_prim_free(p, size, commit, stats); 
        
             if (size >= (SIZE_MAX - alignment)) return NULL; // overflow 
        
             const size_t over_size = size + alignment; 
        
             if (mi_os_mem_config.must_free_whole) {  // win32 virtualAlloc cannot free parts of an allocate block 
        
               // over-allocate uncommitted (virtual) memory 
        
               p = mi_os_prim_alloc(over_size, 1 /*alignment*/, false /* commit? */, false /* allow_large */, is_large, is_zero, stats); 
        
               if (p == NULL) return NULL; 
        
               // set p to the aligned part in the full region 
        
               // note: this is dangerous on Windows as VirtualFree needs the actual base pointer 
        
               // this is handled though by having the `base` field in the memid's 
        
               *base = p; // remember the base 
        
               p = mi_align_up_ptr(p, alignment); 
        
               // explicitly commit only the aligned part 
        
               if (commit) { 
        
                 _mi_os_commit(p, size, NULL, stats); 
        
               } 
        
             }

About guardrail for memory pressure

any changes expected to increase memory above 15% (with a hard limit of 20%) should be discussed with the SC in advance.

Perf run is here waiting for results: https://github.com/facebookexperimental/free-threading-benchmarking/actions/runs/39346123598

@daanx can you please sign the CLA?

Ah yes, but not really for the current PR as that includes the full mimalloc v3 vendored sources and that is a separate project under the MIT license.

I can of course sign off for the changes I made on the CPython side. The current PR contains both, maybe we can split it? I think commit cedd47b is the CPython part only, while the other commits are just importing mimalloc v3 as a vendored library.

FWIW the docs due already call out mimalloc license: https://docs.python.org/3/license.html#mimalloc although we should probably update the date range w/ the v3 update.

perf run is here waiting for results: https://github.com/facebookexperimental/free-threading-benchmarking/actions/runs/39346123598

2x to 1.14x but still higher than mimalloc v2

Suggested change

      
                // Hooks can run under allocator locks, so only consult cached progress.
          
                if (qsbr != NULL) {
          
                    // Scan thread sequences like the v2 integration did.
          
                    return !_Py_qsbr_poll(qsbr, page->goal);
          
                }
          
                // Hooks can run under allocator locks, so only consult cached progress.

Similar logic with

cpython/Objects/obmalloc.c

Line 249 in 4c73f50

if (!_Py_qsbr_poll(tstate->qsbr, page->qsbr_goal)) {

New benchmark run: https://github.com/facebookexperimental/free-threading-benchmarking/actions/runs/39373144391

New benchmark run: https://github.com/facebookexperimental/free-threading-benchmarking/actions/runs/39373144391

That was still a 6% regression on memory (but things are headed in the right direction, THP tweak about it from 2x to 1.15, and then the _Py_qsbr_poll fix got us here), here's another run https://github.com/facebookexperimental/free-threading-benchmarking/actions/runs/39476892845 which has commit 3c8be4f that sets mi_option_purge_delay and mi_option_arena_purge_mult to their v2 values.

Down to a 4% regression now: https://github.com/facebookexperimental/free-threading-benchmarking/tree/main/results/bm-20261020-3.16.0a1+dev-3c8be4f-NOGIL

Another run with new options for mi_option_arena_purge_min_size, and mi_option_page_full_retain and a tweaked mi_option_arena_purge_mult: https://github.com/facebookexperimental/free-threading-benchmarking/actions/runs/39497633255

Down to 3%

This is now neutral: https://github.com/facebookexperimental/free-threading-benchmarking/tree/main/results/bm-20261020-3.16.0a1+dev-a36efb6-NOGIL

It includes one more upstream fix which is a36efb6 that re-enables the mi_arenas_try_purge call which tries to purge expired decommits. This was commented out but not removed in the 3x branch.

@daanx Thanks for merging all of the other upstream PRs I sent. I can send another one to re-enable this but I can also throw it under another ifdef if you're concerned about having it on in the common case. But I think this basically brings us to parity where we could merge this. I'd still want to bring back the latest commits you have upstream but my previous run had that as neutral. I also am assuming your dev3 branch isn't yet released?

daanx added 4 commits October 19, 2026 10:06

Integrate mimalloc v3

cedd47b

Vendor mimalloc v3 snapshot

3bae2f2

update to the latest mimalloc

4b6ebde

update to latest mimalloc

d206e16

Remove trailing whitespace

785620a

github-advanced-security Bot found potential problems Oct 19, 2026

View reviewed changes

Comment thread Objects/mimalloc/util/libc.c Fixed

DinoV added 3 commits October 19, 2026 10:32

Move inline decl

2b6e070

Allow __mi

37b67b6

Fix page size definition on WASI

845a807

DinoV added 6 commits October 19, 2026 11:13

Use relative paths for types

5ce70be

Use " for mimalloc

aa528c3

More quotes

397d08f

Use FLS init

3eb6d6c

Temporarily allow _ZSt

f7a1ffd

Avoid assert dialog

e5fa478

daanx reviewed Oct 19, 2026

View reviewed changes

DinoV added 7 commits October 19, 2026 15:25

Fix msan

98b3858

Set max warnings to 0

fbe3cfe

Emscripten fix?

fde107f

Apply @corona10 tweak to disable THP

e9094bf

Revert "Set max warnings to 0"

a5f4f65

This reverts commit fbe3cfe.

Define MI_TRACK_ASAN for GIL builds

60c5ef6

Include less mimalloc everywhere

e19e2dd

corona10 self-assigned this Oct 20, 2026

corona10 assigned DinoV and itamaro Oct 20, 2026

Disable one more warning

ea0ff6b

corona10 reviewed Oct 20, 2026

View reviewed changes

Use _Py_qsbr_poll when we have an attached thread state to match v2

622cf69

DinoV added 3 commits October 19, 2026 23:00

Better _ZSt15get_new_handlerv fix

568dacd

Fix __ImageBase issue and revert FLS usage

3024497

Set defaults to v2 defaults to reduce memory usage

3c8be4f

DinoV added 3 commits October 20, 2026 12:09

Merge branch 'main' of github.com:python/cpython into mimallocv3

2f699c7

Fix missing endif

97f82e8

Remove mi_fls_key workaround

3ee7565

More options

a8e2a42

DinoV changed the title Mimallocv3 gh-113141: Mimallocv3 Oct 20, 2026

bedevere-app Bot mentioned this pull request Oct 20, 2026

Mimalloc differences from upstream #113141

Open

corona10 mentioned this pull request Oct 20, 2026

gh-131999: Add support for tvOS, visionOS and watchOS. #159944

Open

pure on free?

a36efb6

gh-113141: Mimallocv3 by DinoV · Pull Request #159718 · python/cpython · GitHub

Repository navigation

gh-113141: Mimallocv3 - #159718

gh-113141: Mimallocv3#159718DinoV wants to merge 31 commits intopython:mainpython/cpython:mainfrom DinoV:mimallocv3DinoV/cpython:mimallocv3Copy head branch name to clipboard

Conversation

DinoV commented Oct 19, 2026 • edited by bedevere-app Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

python-cla-bot Bot commented Oct 19, 2026

Uh oh!

read-the-docs-community Bot commented Oct 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Documentation build overview

Uh oh!

Uh oh!

StanFromIreland commented Oct 19, 2026

Uh oh!

daanx commented Oct 19, 2026

Uh oh!

daanx left a comment

Choose a reason for hiding this comment

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

corona10 commented Oct 20, 2026

Uh oh!

corona10 commented Oct 20, 2026

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

corona10 commented Oct 20, 2026

Uh oh!

corona10 Oct 20, 2026

Choose a reason for hiding this comment

Uh oh!

corona10 Oct 20, 2026

Choose a reason for hiding this comment

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

DinoV commented Oct 20, 2026

Uh oh!

DinoV commented Oct 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

DinoV commented Oct 21, 2026

Uh oh!

DinoV commented Oct 21, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

gh-113141: Mimallocv3#159718
DinoV wants to merge 31 commits into
python:mainfrom
DinoV:mimallocv3

DinoV commented Oct 19, 2026 •
edited by bedevere-app Bot
Loading

read-the-docs-community Bot commented Oct 19, 2026 •
edited
Loading

DinoV commented Oct 20, 2026 •
edited
Loading