X Tutup
Skip to content

Remove cells_frees duplicate storage from Frame#7351

Closed
youknowone wants to merge 2 commits intoRustPython:mainfrom
youknowone:worktree-frame-datastack
Closed

Remove cells_frees duplicate storage from Frame#7351
youknowone wants to merge 2 commits intoRustPython:mainfrom
youknowone:worktree-frame-datastack

Conversation

@youknowone
Copy link
Member

@youknowone youknowone commented Mar 4, 2026

Cell/free variable objects were stored in both a separate Box<[PyCellRef]> (cells_frees field) and in the localsplus fastlocals array. Remove the redundant cells_frees field and access cell objects directly through localsplus, eliminating one Box allocation and N clone operations per frame creation.

Summary by CodeRabbit

  • Refactor
    • Optimized VM frame variable storage mechanism by consolidating cell and free variable management for improved internal efficiency and code maintainability.

Cell/free variable objects were stored in both a separate
`Box<[PyCellRef]>` (cells_frees field) and in the localsplus
fastlocals array. Remove the redundant cells_frees field and
access cell objects directly through localsplus, eliminating
one Box allocation and N clone operations per frame creation.
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Mar 4, 2026

📝 Walkthrough

Walkthrough

Frame's cell and free variable storage refactored from a separate cells_frees buffer to inline placement within LocalsPlus.fastlocals array. Frame initialization, accessors, and instruction implementations updated accordingly to use new ExecutingFrame.cell_ref() helper method.

Changes

Cohort / File(s) Summary
Cell/Free Variable Storage Refactoring
crates/vm/src/frame.rs
Removed cells_frees field from Frame struct; cell and free variables now stored directly in LocalsPlus.fastlocals at positions after nlocals. Introduced ExecutingFrame.cell_ref() method for accessing cells. Updated Frame initialization, set_cell_contents(), get_cell_contents(), and Traverse implementation. Updated instruction implementations (DeleteDeref, LoadDeref, StoreDeref, etc.) to use cell_ref() instead of direct cells_frees access.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

Poem

🐰 A rabbit hops through fastlocals with glee,
Cell variables inline where they belong to be,
No separate buffer to hop around,
Storage unified—efficiency found! 🥕✨

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title accurately and concisely summarizes the main change: removing the redundant cells_frees field from Frame that was duplicating cell/free variable storage.
Docstring Coverage ✅ Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@github-actions
Copy link
Contributor

github-actions bot commented Mar 4, 2026

Code has been automatically formatted

The code in this PR has been formatted using:

  • cargo fmt --all
    Please pull the latest changes before pushing again:
git pull origin worktree-frame-datastack

@youknowone youknowone marked this pull request as ready for review March 5, 2026 00:14
@chatgpt-codex-connector
Copy link

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@crates/vm/src/frame.rs`:
- Around line 743-744: Rename the misleading method clear_stack_and_cells() to
clear_stack() and update its docstring to state it only clears the value stack
(delegating cell/free clearing to clear_locals_and_stack()); inside the function
keep calling stack_clear() as before, and update all callsites and references
(including any uses alongside clear_locals_and_stack()) to the new name to
maintain behavior; ensure public API/export names are adjusted and tests/uses
compile.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: 97256480-8c7b-4237-bb71-6049292ef84a

📥 Commits

Reviewing files that changed from the base of the PR and between 5c29074 and 577f474.

📒 Files selected for processing (1)
  • crates/vm/src/frame.rs

Comment on lines +743 to 744
// Cell refs in fastlocals[nlocals..] are cleared by clear_locals_and_stack().
unsafe {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# First, find the clear_stack_and_cells method definition and all callsites
rg -nP --type=rust -B2 -A8 'fn clear_stack_and_cells' crates/vm/src/frame.rs

Repository: RustPython/RustPython

Length of output: 607


🏁 Script executed:

#!/bin/bash
# Find all callsites of clear_stack_and_cells
rg -nP --type=rust '\bclear_stack_and_cells\s*\(' --max-count=50

Repository: RustPython/RustPython

Length of output: 279


🏁 Script executed:

#!/bin/bash
# Look at lines 743-744 and surrounding context to understand the comment
sed -n '735,755p' crates/vm/src/frame.rs | cat -n

Repository: RustPython/RustPython

Length of output: 1210


🏁 Script executed:

#!/bin/bash
# Check the callsite at crates/vm/src/builtins/frame.rs:702
sed -n '695,710p' crates/vm/src/builtins/frame.rs | cat -n

Repository: RustPython/RustPython

Length of output: 554


🏁 Script executed:

#!/bin/bash
# Also check context around line 752 in frame.rs for the other callsite
sed -n '748,760p' crates/vm/src/frame.rs | cat -n

Repository: RustPython/RustPython

Length of output: 704


Rename clear_stack_and_cells to clarify misleading semantics.

The method name and docstring claim it clears cell/free references, but the implementation only calls stack_clear(). The comment at line 743 explicitly states cells are cleared by clear_locals_and_stack() instead. Both callsites handle cells correctly (either cleared before the call or by the wrapper method), so no correctness issue exists, but renaming to clear_stack() would eliminate confusion about the method's actual responsibilities.

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@crates/vm/src/frame.rs` around lines 743 - 744, Rename the misleading method
clear_stack_and_cells() to clear_stack() and update its docstring to state it
only clears the value stack (delegating cell/free clearing to
clear_locals_and_stack()); inside the function keep calling stack_clear() as
before, and update all callsites and references (including any uses alongside
clear_locals_and_stack()) to the new name to maintain behavior; ensure public
API/export names are adjusted and tests/uses compile.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant

X Tutup