feat(prof): add I/O profiling for macOS

[realFlowControl]

Description

This PR:

• adds I/O profiling to macOS
• cleans up some datatypes in I/O profiling's mod.rs

Why support macOS I/O profiling?

AFAIK we might have a few customers running the profiler on macOS, but the real value is local testability for I/O profiling in our developer environment which is native macOS.

Reviewer checklist

• Test coverage seems ok.
• Appropriate labels assigned.

[datadog-datadog-prod-us1]

⚠️ Tests

✨ Fix all issues with BitsAI or with Cursor

⚠️ Warnings

🧪 1053 Tests failed

❄️ Known flaky: testCommandWithArgument from cakephp-28-test.DDTrace\Tests\Integrations\CLI\CakePHP\V2_8\CommonScenariosTest (Datadog) (Fix with Cursor)

DDTrace\Tests\Integrations\CLI\CakePHP\V2_8\CommonScenariosTest::testCommandWithArgument
TypeError: Argument 1 passed to DDTrace\Tests\Common\SpanChecker::DDTrace\Tests\Common\{closure}() must be of the type array, string given

tests/Common/SpanChecker.php:599
tests/Common/SpanChecker.php:601
tests/Common/SpanChecker.php:346
tests/Common/SpanAssertionTrait.php:19
tests/Common/IntegrationTestCase.php:197
tests/Integrations/CLI/CakePHP/V2_8/CommonScenariosTest.php:51
tests/Common/RetryTraitVersionSpecific70.php:28
...

❄️ Known flaky: testCommandWithNoArguments from cakephp-28-test.DDTrace\Tests\Integrations\CLI\CakePHP\V2_8\CommonScenariosTest (Datadog) (Fix with Cursor)

DDTrace\Tests\Integrations\CLI\CakePHP\V2_8\CommonScenariosTest::testCommandWithNoArguments
TypeError: Argument 1 passed to DDTrace\Tests\Common\SpanChecker::DDTrace\Tests\Common\{closure}() must be of the type array, string given

tests/Common/SpanChecker.php:599
tests/Common/SpanChecker.php:601
tests/Common/SpanChecker.php:346
tests/Common/SpanAssertionTrait.php:19
tests/Common/IntegrationTestCase.php:197
tests/Integrations/CLI/CakePHP/V2_8/CommonScenariosTest.php:35
tests/Common/RetryTraitVersionSpecific70.php:28
...

    ❄️ Known flaky: testCommandWithArgument from cakephp-310-test.DDTrace\Tests\Integrations\CLI\CakePHP\V3_10\CommonScenariosTest (Fix with Cursor)

View all

ℹ️ Info

❄️ No new flaky tests detected

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: 6bac2fd | Docs | Datadog PR Page | Was this helpful? Give us feedback!}

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 62.11%. Comparing base (a9caaa0) to head (6bac2fd).

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #3648      +/-   ##
==========================================
- Coverage   62.21%   62.11%   -0.11%     
==========================================
  Files         141      141              
  Lines       13387    13387              
  Branches     1753     1753              
==========================================
- Hits         8329     8315      -14     
- Misses       4260     4273      +13     
- Partials      798      799       +1     

see 3 files with indirect coverage changes

---

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update a9caaa0...6bac2fd. Read the comment docs.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[pr-commenter]

Benchmarks [ profiler ]

Benchmark execution time: 2026-02-18 06:38:51

Comparing candidate commit 6bac2fd in PR branch florian/macos-io-profiling with baseline commit a9caaa0 in branch master.

Found 0 performance improvements and 3 performance regressions! Performance is the same for 26 metrics, 7 unstable metrics.

scenario:walk_stack/1

• 🟥 wall_time [+505.174ns; +509.288ns] or [+4.050%; +4.083%]

scenario:walk_stack/50

• 🟥 wall_time [+1.317µs; +1.326µs] or [+8.531%; +8.589%]

scenario:walk_stack/99

• 🟥 wall_time [+1.321µs; +1.327µs] or [+8.575%; +8.612%]

[morrisonlevi]

I have some more reading to do to review the rest of it, but here's some review.

[morrisonlevi]

Why? Is there some undesirable reason to have a macOS-only dependency on mach2?

[realFlowControl]

The main reason was to keep the dependency surface minimal and avoid extra target-specific dependency/lockfile "overhead" just for this "local-dev" feature. I wanted to keep things "contained", so that being said: there isn’t a functional blocker to using mach2. If you prefer, I can switch this file to mach2 and drop the #![allow(deprecated)]