[PROF-13510] Heap profiling for ruby 4.x by r1viollet · Pull Request #5201 · DataDog/dd-trace-rb

r1viollet · 2026-01-06T17:15:23Z

What does this PR do?

This PR reimplements part of the heap profiler to support Ruby 4 (which was
disabled in #5148 ).

Motivation:

Support heap profiling on Ruby 4!

Change log entry

Yes. Add support for heap profiling on Ruby 4.

For the highlights:

# Heap profiling can now be used on Ruby 4

We've now added support for heap profiling on Ruby 4.0 .
[Check the docs](https://docs.datadoghq.com/profiler/enabling/ruby/?tab=environmentvariables#configuration) for how to enable it.

Additional Notes:

The Datadog Ruby heap profiler tracks live heap objects by storing their object_id when they're allocated, then later using ObjectSpace._id2ref to check if those objects are still alive. This mechanism is currently incompatible with Ruby 4.x.

Key Components

collectors_cpu_and_wall_time_worker.c - Main sampling coordinator
heap_recorder.c - Tracks live heap objects using object IDs

Allocation Flow (Before Fix)

on_newobj_event()  →  start_heap_allocation_recording()  →  end_heap_allocation_recording()
                              ↓
                      rb_obj_id(new_obj)  ← PROBLEM HERE

Liveness Check Flow

heap_recorder_update()  →  st_object_record_update()  →  ruby_ref_from_id()
                                                              ↓
                                                      ObjectSpace._id2ref(obj_id)

The Ruby 4.x Problem

What Changed

Ruby 4.x changed how object_id works internally. The key issue:

on_newobj_event is called during object allocation (object is in "in-between state")
Calling rb_obj_id() during this event mutates the object (assigns an ID)
This mutation is not safe during the allocation tracepoint in Ruby 4.x
Reference: Ruby Issue #21710

Implemented Solution: Deferred Object ID Recording

We defer the rb_obj_id() call to after the allocation tracepoint completes using rb_postponed_job_trigger.

Allocation Flow (After Fix - Ruby 4+)

on_newobj_event()
    ↓
start_heap_allocation_recording()
    - Store VALUE in heap_recorder->active_deferred_object
    - Store metadata in heap_recorder->active_deferred_object_data
    ↓
end_heap_allocation_recording()
    - Move to pending_recordings[] array
    ↓
rb_postponed_job_trigger()
    ↓
finalize_heap_allocation_from_postponed_job()  ← Runs outside allocation tracepoint
    - heap_recorder_finalize_pending_recordings()
    - Call rb_obj_id() safely
    - Commit object_record to heap_record

⚠️ These changes are AI assisted and will require careful review & analysis of performance impacts.

How to test the change?

The usual test coverage uses the new code path on Ruby 4.

We've also added additional coverage in DataDog/prof-correctness#89 + internally in the reliability environment.

github-actions · 2026-01-06T17:15:34Z

Thank you for updating Change log entry section 👏

^{Visited at: 2026-01-29 11:52:43 UTC}

pr-commenter · 2026-01-06T17:43:49Z

Benchmarks

Benchmark execution time: 2026-02-05 15:29:12

Comparing candidate commit e02752c in PR branch r1viollet/heap-profiling-4.0 with baseline commit 1ef92de in branch master.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 44 metrics, 2 unstable metrics.

r1viollet · 2026-01-09T17:00:36Z

Reminder that to measure this, we should do ON/OFF. Some of the cost will be in the VM itself.

datadog-official · 2026-01-09T17:42:23Z

✅ Tests

🎉 All green!

❄️ No new flaky tests detected
🧪 All tests passed

🎯 Code Coverage
• Patch Coverage: 87.10%
• Overall Coverage: 95.15% (-0.01%)

View detailed report

_{This comment will be updated automatically if new data arrives.

🔗 Commit SHA: e02752c | Docs | Datadog PR Page | Was this helpful? Give us feedback!}

ivoanjo

I ran out of time today, here's what I got so far! In particular, I still need to stare at heap_recorder.c for longer, I'm not yet convinced it's correct, I'm seeing some state getting carried across calls that I'm not confident is right.

The current notes are small-ish stuff, other than the extra overhead that's unneeded (and I believe should be easy to fix) + the code exposing the heap recorder directly to the cpu and wall collector that ideally I'd like to avoid too if possible.

ivoanjo

Ok here's my comments from the full pass :)

I think the key change needed is to make sure we call during_sample_enter to avoid any other parts of the profiler firing in the middle of finalization.

Having said that, especially on the heap profiler I'm not a huge fan of some of the duplication -- that code is ultra-fiddly and so having complex logic duplicated across if-defs I worry makes it easy to forget to update one of the versions.

r1viollet · 2026-01-16T15:51:01Z

I took into account major comments.
Next step perf tests.
Then we can do style fixups.

The idea is to delay the time at which we record object ids. Once we are outside of the allocation code path, we can request the object ID.

- Avoid scheduling many postponed jobs This fixes some of the issues we had with accuracy Also I suspect that this has less overhead - Avoid re-entrancy based on Ivo's comments

Although some of this code is dead code on legacy Rubies, always compiling it in means less ifdefs spread throughout and it helps keep the code focused on modern rubies, rather than on legacy ones.

This check is already covered by `heap_recorder->active_recording != NULL` (they're set and unset together).

In the future we may end up using the deferred recording for legacy rubies as well, so might as well lay the groundwork.

ivoanjo · 2026-01-23T11:53:54Z

Quick side-by-side results from Ruby 3.3 vs 4.0 in our Ruby on Rails test app:

**What does this PR do?** This PR adds Ruby 4 heap profiling test variants. As per DataDog/dd-trace-rb#5201, we need a different implementation of heap profiling on Ruby 4, so we want to validate it's still sane with prof-correctness. These variants are effectively the same as the regular ones but: * Replace Ruby 3.3 with Ruby 4.0 * Point to the branch from DataDog/dd-trace-rb#5201 (we'll need to change this back to master once landed) * Set the `DD_PROFILING_EXPERIMENTAL_HEAP_RUBY4_ENABLED` env variable we're using to gate the new feature * Update the `expected_profile.json` to take into account that object allocation in Ruby 4 produces a slightly different stack trace (there's no `new` method on the stack -- it gets inlined into the caller) **Motivation:** Validate Ruby 4 heap profiling. **Additional Notes:** There's still a few anomalies in the results we're looking into... **How to test the change?** Run as usual!

Allow heap profiling to be enabled on Ruby 4 without any extra flags.

ivoanjo · 2026-01-29T11:53:17Z

TODO: We're still investigating a few benchmarks / validation results, but this should be ready for review.

AlexJF

Looks mostly good to me. Some minor feedback to try to prevent so much split logic.

Also, if the deferred mechanism is also compatible with Ruby < 4, could it make sense to unify codepaths and have all be deferred? Or does this incur a perf penalty?

r1viollet

LGTM (can't approve as I opened this)
Though feel free to merge.
I was thinking that a test that would exercise some of the raise code paths could be good, though not blocking for this PR.
Performance looks the same as other heap instrumentation.
Accuracy tests are OK.

`end_heap_allocation_recording` should not be called directly, we always go through `end_heap_allocation_recording_with_rb_protect` and thus observing `SKIPPED_RECORD` inside `end_heap_allocation_recording` is a bug.

ivoanjo · 2026-02-05T15:52:07Z

I think this is good shape! Pressing the nice green button!

github-actions Bot added the profiling Involves Datadog profiling label Jan 6, 2026

r1viollet force-pushed the r1viollet/heap-profiling-4.0 branch from c4fdb76 to 49477bf Compare January 6, 2026 17:46

ivoanjo reviewed Jan 13, 2026

View reviewed changes

ivoanjo reviewed Jan 14, 2026

View reviewed changes

r1viollet force-pushed the r1viollet/heap-profiling-4.0 branch 2 times, most recently from e966c43 to ea9eba7 Compare January 16, 2026 15:50

github-actions Bot added the core Involves Datadog core libraries label Jan 16, 2026

r1viollet force-pushed the r1viollet/heap-profiling-4.0 branch from ea9eba7 to 4dbdd06 Compare January 19, 2026 08:32

r1viollet commented Jan 19, 2026

View reviewed changes

Comment thread spec/datadog/profiling/stack_recorder_spec.rb

ivoanjo changed the title ~~Heap profiling for ruby 4.x - Prototype~~ [PROF-13510] Heap profiling for ruby 4.x - Prototype Jan 20, 2026

r1viollet and others added 15 commits January 21, 2026 14:28

Heap profiling for ruby 4.x - Prototype

9564ca6

The idea is to delay the time at which we record object ids. Once we are outside of the allocation code path, we can request the object ID.

heap profiling 4.x - Remove unnecessary check

b5e5175

Heap profiling 4.x: fix compilation warning for ruby <4 versions

b7a82ad

profiling: heap 4.x - Batch postoned jobs & fixes

5668338

- Avoid scheduling many postponed jobs This fixes some of the issues we had with accuracy Also I suspect that this has less overhead - Avoid re-entrancy based on Ivo's comments

Heap profiling 4.x - Adjust error handling & flag naming

660f7f4

profiling heap profiling for ruby4: add an experimental flag & fixups

34f28d7

Profiling experimental 4.0 support - Add a changelog entry

e153759

Remove a few of the ifdefs to simplify code

ce75c22

Although some of this code is dead code on legacy Rubies, always compiling it in means less ifdefs spread throughout and it helps keep the code focused on modern rubies, rather than on legacy ones.

Minor: Remove check for active_deferred_object

9d5aa45

This check is already covered by `heap_recorder->active_recording != NULL` (they're set and unset together).

Minor: Move error checking closer to return

851e439

Minor: Simplify marking code

a15509f

Make env flag to enable ruby 4 heap profiler internal for now

68ec35c

Tweak testing of heap profiling enabling logic

f412be4

Minor: Simplify new stats by removing ifdefs

1e9c1d6

Fix C to Ruby conversions that should be unsigned

e1c9925

ivoanjo added 7 commits January 22, 2026 10:49

Reduce ifdefs, just let legacy rubies compile code too

6fdb2c8

In the future we may end up using the deferred recording for legacy rubies as well, so might as well lay the groundwork.

Small simplifications

698b334

More small simplifications

b881957

Extract out common code in a slightly different way

3a671f6

Remove header reference (not available on all Rubies)

a383a19

Merge branch 'master' into r1viollet/heap-profiling-4.0

ce3c746

Make linter happy

cb3ef5e

ivoanjo mentioned this pull request Jan 29, 2026

[PROF-13510] Add Ruby 4 heap profiling test variants DataDog/prof-correctness#89

Merged

Get rid of DD_PROFILING_EXPERIMENTAL_HEAP_RUBY4_ENABLED

a64a546

Allow heap profiling to be enabled on Ruby 4 without any extra flags.

ivoanjo changed the title ~~[PROF-13510] Heap profiling for ruby 4.x - Prototype~~ [PROF-13510] Heap profiling for ruby 4.x Jan 29, 2026

ivoanjo marked this pull request as ready for review January 29, 2026 11:53

ivoanjo requested review from a team as code owners January 29, 2026 11:53

ivoanjo requested a review from AlexJF January 29, 2026 11:53

AlexJF approved these changes Feb 2, 2026

View reviewed changes

Comment thread ext/datadog_profiling_native_extension/heap_recorder.c Outdated

Comment thread ext/datadog_profiling_native_extension/heap_recorder.c

r1viollet commented Feb 2, 2026

View reviewed changes

Comment thread ext/datadog_profiling_native_extension/heap_recorder.c

r1viollet commented Feb 4, 2026

View reviewed changes

ivoanjo added 3 commits February 5, 2026 14:32

Minor: Extract out needs_after_allocation to simplify code

e77f801

Minor: &SKIPPED_RECORD should not show up inside this function

f06a731

`end_heap_allocation_recording` should not be called directly, we always go through `end_heap_allocation_recording_with_rb_protect` and thus observing `SKIPPED_RECORD` inside `end_heap_allocation_recording` is a bug.

Merge branch 'master' into r1viollet/heap-profiling-4.0

e02752c

ivoanjo merged commit 7631952 into master Feb 5, 2026
762 of 764 checks passed

ivoanjo deleted the r1viollet/heap-profiling-4.0 branch February 5, 2026 15:52

github-actions Bot added this to the 2.29.0 milestone Feb 5, 2026

y9v mentioned this pull request Feb 20, 2026

Bump to version 2.29.0 #5383

Merged

navidemad mentioned this pull request Jun 23, 2026

[BUG]: SIGSEGV in heap_recorder.c (st_object_record_update → ruby_obj_memsize_of → classext_memsize) on Ruby 4.0 with heap size profiling #5936

Open

Uh oh!

Conversation

r1viollet commented Jan 6, 2026 • edited by ivoanjo Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Key Components

Allocation Flow (Before Fix)

Liveness Check Flow

The Ruby 4.x Problem

What Changed

Implemented Solution: Deferred Object ID Recording

Allocation Flow (After Fix - Ruby 4+)

Uh oh!

github-actions Bot commented Jan 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pr-commenter Bot commented Jan 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Benchmarks

Uh oh!

r1viollet commented Jan 9, 2026

Uh oh!

datadog-official Bot commented Jan 9, 2026 • edited by datadog-datadog-prod-us1 Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ivoanjo left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ivoanjo left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

r1viollet commented Jan 16, 2026

Uh oh!

Uh oh!

ivoanjo commented Jan 23, 2026

Uh oh!

ivoanjo commented Jan 29, 2026

Uh oh!

AlexJF left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

r1viollet left a comment

Choose a reason for hiding this comment

Uh oh!

ivoanjo commented Feb 5, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

r1viollet commented Jan 6, 2026 •

edited by ivoanjo

Loading

github-actions Bot commented Jan 6, 2026 •

edited

Loading

pr-commenter Bot commented Jan 6, 2026 •

edited

Loading

datadog-official Bot commented Jan 9, 2026 •

edited by datadog-datadog-prod-us1 Bot

Loading