[connortsui20]

Summary

The CodSpeed report on #10990 flags test_scan[int_str] as dominated by system calls. Its trace attributes about 314 ms to condition-variable wakeups under the async I/O reactor.

Changes

Runs Python CPU simulation with VORTEX_MAX_THREADS=0 and memory-maps the shared benchmark files, so scans execute on the calling thread without dispatching file reads to I/O threads. This changes the scan, filter, and scalar-access benchmark setup, including repeated scans.

Pre-commit formatting and sign-off checks passed. Workspace Clippy was started by the push hook and interrupted. Tests and CodSpeed have not been rerun, so clearing the warning still needs CI confirmation.

[codspeed]

Merging this PR will improve performance by 11.23%

1 warning

⚠️ Walltime results may be unreliable

Some benchmarks used the Walltime instrument outside CodSpeed Macro Runners, which can make the results inconsistent.

Learn more about Macro Runners

See affected benchmarks

⚡ 2 improved benchmarks
✅ 2304 untouched benchmarks
🗄️ 47 archived benchmarks run¹

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
⚡	Walltime	threshold_avx2[80]	3 µs	2.7 µs	+12.39%
⚡	CPU Simulation	test_repeated_scan_scalar_at[int_float]	308.3 µs	280 µs	+10.08%

Tip

Curious why performance improved? Comment @codspeedbot explain why performance improved on this PR, or directly use the CodSpeed MCP with your agent.

---

_{Comparing ct/python-scan-simulation (55028ca) with develop (c6d6bad)}

Footnotes

1. 47 benchmarks were run, but are now archived. If they were deleted in another branch, consider rebasing to remove them from the report. Instead if they were added back, click here to restore them. ↩

[robert3005]

I think for simulation this makes sense