Skip to content

fix(profiling): do not remove links for just-created Tasks #15552

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
KowalskiThomas merged 1 commit into from
Dec 9, 2025
Merged

fix(profiling): do not remove links for just-created Tasks #15552

KowalskiThomas merged 1 commit into from
Dec 9, 2025

Conversation

@KowalskiThomas
Copy link
Contributor

@KowalskiThomas KowalskiThomas commented Dec 8, 2025 •
edited
Loading

Description

Echion PR: P403n1x87/echion#210

This PR fixes a race condition happening around linking Parent and Children Tasks when using utilities like asyncio.gather or asyncio.as_completed.

The problem

The race condition would manifest in the following way

  1. User calls e.g. asyncio.as_completed from parent_task
  2. Our patch creates Tasks for each awaitable passed to the function and inserts resulting Task objects into the Task Links Map (one of each is new_task)
  3. A Sample is taken exactly at that moment, Task Link Map cleanup logic kicks in.
    a. new_task was created only just now, so was not part of the all_tasks MirrorSet snapshotted by the Sampler
    b. The cleanup logic sees that there's a link from new_task to parent_task but new_task isn't in all_tasks
    c. The cleanup logic assumes that means new_task previously existed but has completed, deduces the link must be removed
    d. Link is removed
  4. new_task starts executing, but isn't linked to parent_task because we've cleaned it up before it got a chance to start

Proposed fix

The fix I propose is to introduce a new previous_task_objects set which contains the addresses of all existing Task objects at the time we previously sampled.
If we see a Task object in the Task Links Map that doesn't exist in all_tasks, then two things are possible: either the Task used to exist and the link should be removed, or the Task was just created and the link should stay. To determine which case we're in, we look at previous_task_objects – if the Task is there then it previously existed and just completed (⇒ need to remove); if not, it was just created (⇒ shouldn't remove).

Admitted caveat

I think this comes with one caveat: if we sample very rarely (which may happen in certain circumstances with adaptive sampling), then we could miss certain Tasks and never get rid of their links:

async def super_quick():
  return None

async def parent():
  await asyncio.sleep(1.0)
  asyncio.gather(asyncio.create_task(super_quick()))

Given that super_quick will be… super quick, the following could happen:

  • We sample; we see parent ; all_tasks = { parent }; task_links = {} ; previous_all_tasks = { parent }
  • Parent continues, calls asyncio.gather(...) creates another Task ; all_tasks = { parent, super_quick }; task_links = { super_quick -> parent }
  • (We don’t sample yet because we rarely sample…)
  • Task execution continues, super_quick runs super quickly and finishes ; all_tasks = { parent }; task_links = { super_quick -> parent }
  • We sample; we see only parent (only Task in existence at that point); current all_tasks = { parent };
    • previous_all_tasks = { parent } (still from the first sample we took) and task_links = { super_quick -> parent }
    • Our “debouncing” logic considers that super_quick is a new Task [because it’s not in previous_all_tasks] and doesn’t remove the link

⇒ The link will never go away because we’ll keep repeating this (potentially adding/removing other Tasks and Links, but this specific one will stay forever)

Additional change

The PR also fixes an issue with our patch for as_completed that would crash if parent was None. I don't think this can ever happen (since as_completed is necessarily called from a Task), but better safe than sorry.

Testing

As this change fixes a race condition, it is pretty hard to strictly speaking test it. dd-trace-py already has a test that flaked in the past due to it (and that flaked in Echion as well): test_asyncio_as_completed

@KowalskiThomas KowalskiThomas requested a review from a team as a code owner December 8, 2025 16:49
@KowalskiThomas KowalskiThomas added the Profiling Continous Profling label Dec 8, 2025
@github-actions
Copy link
Contributor

github-actions bot commented Dec 8, 2025 •
edited
Loading

CODEOWNERS have been resolved as:

releasenotes/notes/profiling-fix-task-link-race-condition-891ac5c86af8a7c1.yaml  @DataDog/apm-python
ddtrace/internal/datadog/profiling/stack_v2/echion/echion/threads.h     @DataDog/profiling-python
tests/profiling/collector/test_asyncio_as_completed.py                  @DataDog/profiling-python

@KowalskiThomas KowalskiThomas force-pushed the kowalski/fix-profiling-do-not-remove-links-for-just-created-tasks branch from 3efe284 to 5b8add2 Compare December 8, 2025 16:50
@KowalskiThomas KowalskiThomas requested a review from a team as a code owner December 8, 2025 16:50
taegyunkim
taegyunkim reviewed Dec 8, 2025
View reviewed changes
Copy link
Contributor

@taegyunkim taegyunkim left a comment

Choose a reason for hiding this comment

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

Would it be possible to have a test case with what you wrote in the PR description?

@github-actions
Copy link
Contributor

github-actions bot commented Dec 8, 2025 •
edited
Loading

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 250 ± 3 ms.

The average import time from base is: 252 ± 3 ms.

The import time difference between this PR and base is: -2.6 ± 0.1 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.652 ms (1.06%)
ddtrace 1.356 ms (0.54%)
ddtrace._logger 0.677 ms (0.27%)
ddtrace.internal.telemetry 0.677 ms (0.27%)
ddtrace.internal.telemetry.writer 0.677 ms (0.27%)
ddtrace.internal.utils.version 0.677 ms (0.27%)
ddtrace.version 0.677 ms (0.27%)
ddtrace.internal._unpatched 0.029 ms (0.01%)
json 0.029 ms (0.01%)
json.decoder 0.029 ms (0.01%)
re 0.029 ms (0.01%)
enum 0.029 ms (0.01%)
types 0.029 ms (0.01%)
ddtrace.bootstrap.sitecustomize 1.296 ms (0.52%)
ddtrace.bootstrap.preload 1.296 ms (0.52%)
ddtrace.internal.remoteconfig.client 0.645 ms (0.26%)

@pr-commenter
Copy link

pr-commenter bot commented Dec 8, 2025 •
edited
Loading

Performance SLOs

Comparing candidate kowalski/fix-profiling-do-not-remove-links-for-just-created-tasks (a7baa36) with baseline main (73210fe)

📈 Performance Regressions (3 suites)
📈 iastaspects - 118/118

✅ add_aspect

Time: ✅ 0.406µs (SLO: <10.000µs 📉 -95.9%) vs baseline: +0.9%

Memory: ✅ 40.161MB (SLO: <41.500MB -3.2%) vs baseline: +4.3%

✅ add_inplace_aspect

Time: ✅ 0.406µs (SLO: <10.000µs 📉 -95.9%) vs baseline: -1.2%

Memory: ✅ 40.187MB (SLO: <41.500MB -3.2%) vs baseline: +4.4%

✅ add_inplace_noaspect

Time: ✅ 0.322µs (SLO: <10.000µs 📉 -96.8%) vs baseline: +1.6%

Memory: ✅ 40.159MB (SLO: <41.500MB -3.2%) vs baseline: +4.8%

✅ add_noaspect

Time: ✅ 0.278µs (SLO: <10.000µs 📉 -97.2%) vs baseline: +0.5%

Memory: ✅ 40.202MB (SLO: <41.500MB -3.1%) vs baseline: +4.9%

✅ bytearray_aspect

Time: ✅ 1.354µs (SLO: <10.000µs 📉 -86.5%) vs baseline: +1.1%

Memory: ✅ 40.239MB (SLO: <41.500MB -3.0%) vs baseline: +4.7%

✅ bytearray_extend_aspect

Time: ✅ 1.497µs (SLO: <10.000µs 📉 -85.0%) vs baseline: -1.3%

Memory: ✅ 40.223MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ bytearray_extend_noaspect

Time: ✅ 0.614µs (SLO: <10.000µs 📉 -93.9%) vs baseline: ~same

Memory: ✅ 40.160MB (SLO: <41.500MB -3.2%) vs baseline: +4.2%

✅ bytearray_noaspect

Time: ✅ 0.491µs (SLO: <10.000µs 📉 -95.1%) vs baseline: +2.9%

Memory: ✅ 40.178MB (SLO: <41.500MB -3.2%) vs baseline: +4.6%

✅ bytes_aspect

Time: ✅ 1.296µs (SLO: <10.000µs 📉 -87.0%) vs baseline: -0.4%

Memory: ✅ 40.301MB (SLO: <41.500MB -2.9%) vs baseline: +4.9%

✅ bytes_noaspect

Time: ✅ 0.497µs (SLO: <10.000µs 📉 -95.0%) vs baseline: +1.3%

Memory: ✅ 40.119MB (SLO: <41.500MB -3.3%) vs baseline: +4.7%

✅ bytesio_aspect

Time: ✅ 1.359µs (SLO: <10.000µs 📉 -86.4%) vs baseline: +3.8%

Memory: ✅ 40.200MB (SLO: <41.500MB -3.1%) vs baseline: +4.9%

✅ bytesio_noaspect

Time: ✅ 0.499µs (SLO: <10.000µs 📉 -95.0%) vs baseline: +0.3%

Memory: ✅ 40.118MB (SLO: <41.500MB -3.3%) vs baseline: +4.5%

✅ capitalize_aspect

Time: ✅ 0.738µs (SLO: <10.000µs 📉 -92.6%) vs baseline: -0.3%

Memory: ✅ 40.238MB (SLO: <41.500MB -3.0%) vs baseline: +4.9%

✅ capitalize_noaspect

Time: ✅ 0.435µs (SLO: <10.000µs 📉 -95.6%) vs baseline: ~same

Memory: ✅ 40.119MB (SLO: <41.500MB -3.3%) vs baseline: +4.6%

✅ casefold_aspect

Time: ✅ 0.737µs (SLO: <10.000µs 📉 -92.6%) vs baseline: -0.3%

Memory: ✅ 40.278MB (SLO: <41.500MB -2.9%) vs baseline: +5.1%

✅ casefold_noaspect

Time: ✅ 0.367µs (SLO: <10.000µs 📉 -96.3%) vs baseline: -0.8%

Memory: ✅ 40.040MB (SLO: <41.500MB -3.5%) vs baseline: +4.7%

✅ decode_aspect

Time: ✅ 0.718µs (SLO: <10.000µs 📉 -92.8%) vs baseline: -0.4%

Memory: ✅ 40.239MB (SLO: <41.500MB -3.0%) vs baseline: +5.0%

✅ decode_noaspect

Time: ✅ 0.417µs (SLO: <10.000µs 📉 -95.8%) vs baseline: -0.5%

Memory: ✅ 40.358MB (SLO: <41.500MB -2.8%) vs baseline: +4.6%

✅ encode_aspect

Time: ✅ 0.708µs (SLO: <10.000µs 📉 -92.9%) vs baseline: +0.2%

Memory: ✅ 40.219MB (SLO: <41.500MB -3.1%) vs baseline: +5.0%

✅ encode_noaspect

Time: ✅ 0.405µs (SLO: <10.000µs 📉 -96.0%) vs baseline: +0.6%

Memory: ✅ 40.278MB (SLO: <41.500MB -2.9%) vs baseline: +4.8%

✅ format_aspect

Time: ✅ 3.450µs (SLO: <10.000µs 📉 -65.5%) vs baseline: +0.6%

Memory: ✅ 40.296MB (SLO: <41.500MB -2.9%) vs baseline: +4.7%

✅ format_map_aspect

Time: ✅ 3.530µs (SLO: <10.000µs 📉 -64.7%) vs baseline: -1.4%

Memory: ✅ 40.199MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ format_map_noaspect

Time: ✅ 0.774µs (SLO: <10.000µs 📉 -92.3%) vs baseline: -0.3%

Memory: ✅ 40.218MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ format_noaspect

Time: ✅ 0.595µs (SLO: <10.000µs 📉 -94.0%) vs baseline: +0.4%

Memory: ✅ 40.119MB (SLO: <41.500MB -3.3%) vs baseline: +4.2%

✅ index_aspect

Time: ✅ 0.358µs (SLO: <10.000µs 📉 -96.4%) vs baseline: +1.1%

Memory: ✅ 40.280MB (SLO: <41.500MB -2.9%) vs baseline: +4.8%

✅ index_noaspect

Time: ✅ 0.278µs (SLO: <10.000µs 📉 -97.2%) vs baseline: -0.9%

Memory: ✅ 40.081MB (SLO: <41.500MB -3.4%) vs baseline: +4.5%

✅ join_aspect

Time: ✅ 1.337µs (SLO: <10.000µs 📉 -86.6%) vs baseline: +0.4%

Memory: ✅ 40.121MB (SLO: <41.500MB -3.3%) vs baseline: +4.2%

✅ join_noaspect

Time: ✅ 0.491µs (SLO: <10.000µs 📉 -95.1%) vs baseline: +0.3%

Memory: ✅ 40.221MB (SLO: <41.500MB -3.1%) vs baseline: +4.8%

✅ ljust_aspect

Time: ✅ 2.651µs (SLO: <20.000µs 📉 -86.7%) vs baseline: +3.5%

Memory: ✅ 40.316MB (SLO: <41.500MB -2.9%) vs baseline: +4.7%

✅ ljust_noaspect

Time: ✅ 0.403µs (SLO: <10.000µs 📉 -96.0%) vs baseline: -1.9%

Memory: ✅ 40.338MB (SLO: <41.500MB -2.8%) vs baseline: +5.1%

✅ lower_aspect

Time: ✅ 2.308µs (SLO: <10.000µs 📉 -76.9%) vs baseline: +3.1%

Memory: ✅ 40.116MB (SLO: <41.500MB -3.3%) vs baseline: +4.8%

✅ lower_noaspect

Time: ✅ 0.366µs (SLO: <10.000µs 📉 -96.3%) vs baseline: -0.3%

Memory: ✅ 40.159MB (SLO: <41.500MB -3.2%) vs baseline: +4.4%

✅ lstrip_aspect

Time: ✅ 2.253µs (SLO: <20.000µs 📉 -88.7%) vs baseline: -0.2%

Memory: ✅ 40.296MB (SLO: <41.500MB -2.9%) vs baseline: +5.1%

✅ lstrip_noaspect

Time: ✅ 0.379µs (SLO: <10.000µs 📉 -96.2%) vs baseline: -1.0%

Memory: ✅ 40.299MB (SLO: <41.500MB -2.9%) vs baseline: +4.5%

✅ modulo_aspect

Time: ✅ 1.049µs (SLO: <10.000µs 📉 -89.5%) vs baseline: +4.8%

Memory: ✅ 40.140MB (SLO: <41.500MB -3.3%) vs baseline: +4.3%

✅ modulo_aspect_for_bytearray_bytearray

Time: ✅ 1.541µs (SLO: <10.000µs 📉 -84.6%) vs baseline: -1.4%

Memory: ✅ 40.161MB (SLO: <41.500MB -3.2%) vs baseline: +4.4%

✅ modulo_aspect_for_bytes

Time: ✅ 0.981µs (SLO: <10.000µs 📉 -90.2%) vs baseline: -1.0%

Memory: ✅ 40.280MB (SLO: <41.500MB -2.9%) vs baseline: +5.1%

✅ modulo_aspect_for_bytes_bytearray

Time: ✅ 1.247µs (SLO: <10.000µs 📉 -87.5%) vs baseline: +2.4%

Memory: ✅ 40.143MB (SLO: <41.500MB -3.3%) vs baseline: +4.4%

✅ modulo_noaspect

Time: ✅ 0.627µs (SLO: <10.000µs 📉 -93.7%) vs baseline: ~same

Memory: ✅ 40.278MB (SLO: <41.500MB -2.9%) vs baseline: +5.3%

✅ replace_aspect

Time: ✅ 4.868µs (SLO: <10.000µs 📉 -51.3%) vs baseline: -0.5%

Memory: ✅ 40.202MB (SLO: <41.500MB -3.1%) vs baseline: +4.6%

✅ replace_noaspect

Time: ✅ 0.464µs (SLO: <10.000µs 📉 -95.4%) vs baseline: +1.7%

Memory: ✅ 40.199MB (SLO: <41.500MB -3.1%) vs baseline: +4.7%

✅ repr_aspect

Time: ✅ 0.905µs (SLO: <10.000µs 📉 -91.0%) vs baseline: -0.1%

Memory: ✅ 40.357MB (SLO: <41.500MB -2.8%) vs baseline: +5.3%

✅ repr_noaspect

Time: ✅ 0.421µs (SLO: <10.000µs 📉 -95.8%) vs baseline: +0.9%

Memory: ✅ 40.241MB (SLO: <41.500MB -3.0%) vs baseline: +4.7%

✅ rstrip_aspect

Time: ✅ 1.968µs (SLO: <20.000µs 📉 -90.2%) vs baseline: +1.9%

Memory: ✅ 40.156MB (SLO: <41.500MB -3.2%) vs baseline: +4.5%

✅ rstrip_noaspect

Time: ✅ 0.382µs (SLO: <10.000µs 📉 -96.2%) vs baseline: +1.9%

Memory: ✅ 40.239MB (SLO: <41.500MB -3.0%) vs baseline: +4.9%

✅ slice_aspect

Time: ✅ 0.493µs (SLO: <10.000µs 📉 -95.1%) vs baseline: -0.4%

Memory: ✅ 40.301MB (SLO: <41.500MB -2.9%) vs baseline: +4.8%

✅ slice_noaspect

Time: ✅ 0.446µs (SLO: <10.000µs 📉 -95.5%) vs baseline: +0.4%

Memory: ✅ 40.259MB (SLO: <41.500MB -3.0%) vs baseline: +5.2%

✅ stringio_aspect

Time: ✅ 1.764µs (SLO: <10.000µs 📉 -82.4%) vs baseline: 📈 +14.7%

Memory: ✅ 40.300MB (SLO: <41.500MB -2.9%) vs baseline: +5.3%

✅ stringio_noaspect

Time: ✅ 0.711µs (SLO: <10.000µs 📉 -92.9%) vs baseline: -0.1%

Memory: ✅ 40.100MB (SLO: <41.500MB -3.4%) vs baseline: +4.5%

✅ strip_aspect

Time: ✅ 2.241µs (SLO: <20.000µs 📉 -88.8%) vs baseline: +0.6%

Memory: ✅ 40.396MB (SLO: <41.500MB -2.7%) vs baseline: +5.1%

✅ strip_noaspect

Time: ✅ 0.382µs (SLO: <10.000µs 📉 -96.2%) vs baseline: -1.2%

Memory: ✅ 40.240MB (SLO: <41.500MB -3.0%) vs baseline: +4.8%

✅ swapcase_aspect

Time: ✅ 2.522µs (SLO: <10.000µs 📉 -74.8%) vs baseline: +3.5%

Memory: ✅ 40.379MB (SLO: <41.500MB -2.7%) vs baseline: +4.9%

✅ swapcase_noaspect

Time: ✅ 0.541µs (SLO: <10.000µs 📉 -94.6%) vs baseline: +1.1%

Memory: ✅ 40.200MB (SLO: <41.500MB -3.1%) vs baseline: +5.0%

✅ title_aspect

Time: ✅ 2.432µs (SLO: <10.000µs 📉 -75.7%) vs baseline: +2.1%

Memory: ✅ 40.196MB (SLO: <41.500MB -3.1%) vs baseline: +4.7%

✅ title_noaspect

Time: ✅ 0.507µs (SLO: <10.000µs 📉 -94.9%) vs baseline: +0.3%

Memory: ✅ 40.220MB (SLO: <41.500MB -3.1%) vs baseline: +4.5%

✅ translate_aspect

Time: ✅ 3.329µs (SLO: <10.000µs 📉 -66.7%) vs baseline: +0.2%

Memory: ✅ 40.260MB (SLO: <41.500MB -3.0%) vs baseline: +4.5%

✅ translate_noaspect

Time: ✅ 1.043µs (SLO: <10.000µs 📉 -89.6%) vs baseline: +0.2%

Memory: ✅ 40.021MB (SLO: <41.500MB -3.6%) vs baseline: +4.5%

✅ upper_aspect

Time: ✅ 2.324µs (SLO: <10.000µs 📉 -76.8%) vs baseline: +2.3%

Memory: ✅ 40.136MB (SLO: <41.500MB -3.3%) vs baseline: +4.9%

✅ upper_noaspect

Time: ✅ 0.370µs (SLO: <10.000µs 📉 -96.3%) vs baseline: +0.1%

Memory: ✅ 40.140MB (SLO: <41.500MB -3.3%) vs baseline: +4.5%

📈 iastaspectsospath - 24/24

✅ ospathbasename_aspect

Time: ✅ 5.180µs (SLO: <10.000µs 📉 -48.2%) vs baseline: 📈 +26.5%

Memory: ✅ 40.187MB (SLO: <41.000MB 🟡 -2.0%) vs baseline: +4.5%

✅ ospathbasename_noaspect

Time: ✅ 1.097µs (SLO: <10.000µs 📉 -89.0%) vs baseline: +0.3%

Memory: ✅ 40.246MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +5.1%

✅ ospathjoin_aspect

Time: ✅ 6.217µs (SLO: <10.000µs 📉 -37.8%) vs baseline: +0.6%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.4%

✅ ospathjoin_noaspect

Time: ✅ 2.293µs (SLO: <10.000µs 📉 -77.1%) vs baseline: -0.2%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.9%

✅ ospathnormcase_aspect

Time: ✅ 3.423µs (SLO: <10.000µs 📉 -65.8%) vs baseline: -0.7%

Memory: ✅ 40.305MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +4.9%

✅ ospathnormcase_noaspect

Time: ✅ 0.568µs (SLO: <10.000µs 📉 -94.3%) vs baseline: -1.3%

Memory: ✅ 40.167MB (SLO: <41.000MB -2.0%) vs baseline: +4.8%

✅ ospathsplit_aspect

Time: ✅ 4.741µs (SLO: <10.000µs 📉 -52.6%) vs baseline: -0.6%

Memory: ✅ 40.187MB (SLO: <41.000MB 🟡 -2.0%) vs baseline: +4.9%

✅ ospathsplit_noaspect

Time: ✅ 1.606µs (SLO: <10.000µs 📉 -83.9%) vs baseline: +1.4%

Memory: ✅ 40.305MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.0%

✅ ospathsplitdrive_aspect

Time: ✅ 3.638µs (SLO: <10.000µs 📉 -63.6%) vs baseline: -0.7%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.7%

✅ ospathsplitdrive_noaspect

Time: ✅ 0.702µs (SLO: <10.000µs 📉 -93.0%) vs baseline: -2.1%

Memory: ✅ 40.167MB (SLO: <41.000MB -2.0%) vs baseline: +4.6%

✅ ospathsplitext_aspect

Time: ✅ 4.526µs (SLO: <10.000µs 📉 -54.7%) vs baseline: +1.1%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +4.5%

✅ ospathsplitext_noaspect

Time: ✅ 1.386µs (SLO: <10.000µs 📉 -86.1%) vs baseline: -0.2%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.8%

📈 telemetryaddmetric - 30/30

✅ 1-count-metric-1-times

Time: ✅ 3.375µs (SLO: <20.000µs 📉 -83.1%) vs baseline: 📈 +14.5%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.7%

✅ 1-count-metrics-100-times

Time: ✅ 199.606µs (SLO: <220.000µs -9.3%) vs baseline: -0.9%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.0%

✅ 1-distribution-metric-1-times

Time: ✅ 3.288µs (SLO: <20.000µs 📉 -83.6%) vs baseline: -0.1%

Memory: ✅ 35.075MB (SLO: <35.500MB 🟡 -1.2%) vs baseline: +4.9%

✅ 1-distribution-metrics-100-times

Time: ✅ 216.689µs (SLO: <230.000µs -5.8%) vs baseline: ~same

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.1%

✅ 1-gauge-metric-1-times

Time: ✅ 2.156µs (SLO: <20.000µs 📉 -89.2%) vs baseline: -1.7%

Memory: ✅ 34.623MB (SLO: <35.500MB -2.5%) vs baseline: +4.0%

✅ 1-gauge-metrics-100-times

Time: ✅ 135.954µs (SLO: <150.000µs -9.4%) vs baseline: +0.5%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +3.9%

✅ 1-rate-metric-1-times

Time: ✅ 3.101µs (SLO: <20.000µs 📉 -84.5%) vs baseline: -0.2%

Memory: ✅ 35.075MB (SLO: <35.500MB 🟡 -1.2%) vs baseline: +5.8%

✅ 1-rate-metrics-100-times

Time: ✅ 213.307µs (SLO: <250.000µs 📉 -14.7%) vs baseline: -1.3%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +4.9%

✅ 100-count-metrics-100-times

Time: ✅ 20.152ms (SLO: <22.000ms -8.4%) vs baseline: -0.7%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.9%

✅ 100-distribution-metrics-100-times

Time: ✅ 2.253ms (SLO: <2.550ms 📉 -11.6%) vs baseline: -0.5%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.7%

✅ 100-gauge-metrics-100-times

Time: ✅ 1.404ms (SLO: <1.550ms -9.4%) vs baseline: -0.5%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +5.1%

✅ 100-rate-metrics-100-times

Time: ✅ 2.198ms (SLO: <2.550ms 📉 -13.8%) vs baseline: -0.5%

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +5.1%

✅ flush-1-metric

Time: ✅ 4.591µs (SLO: <20.000µs 📉 -77.0%) vs baseline: -1.0%

Memory: ✅ 35.075MB (SLO: <35.500MB 🟡 -1.2%) vs baseline: +4.9%

✅ flush-100-metrics

Time: ✅ 174.530µs (SLO: <250.000µs 📉 -30.2%) vs baseline: ~same

Memory: ✅ 35.193MB (SLO: <35.500MB 🟡 -0.9%) vs baseline: +4.7%

✅ flush-1000-metrics

Time: ✅ 2.174ms (SLO: <2.500ms 📉 -13.1%) vs baseline: -0.4%

Memory: ✅ 35.940MB (SLO: <36.500MB 🟡 -1.5%) vs baseline: +5.1%

🟡 Near SLO Breach (17 suites)
🟡 coreapiscenario - 10/10 (1 unstable)

⚠️ context_with_data_listeners

Time: ⚠️ 13.264µs (SLO: <20.000µs 📉 -33.7%) vs baseline: ~same

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.6%

✅ context_with_data_no_listeners

Time: ✅ 3.255µs (SLO: <10.000µs 📉 -67.5%) vs baseline: -0.9%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.9%

✅ get_item_exists

Time: ✅ 0.582µs (SLO: <10.000µs 📉 -94.2%) vs baseline: ~same

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.1%

✅ get_item_missing

Time: ✅ 0.641µs (SLO: <10.000µs 📉 -93.6%) vs baseline: +1.3%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +5.0%

✅ set_item

Time: ✅ 24.254µs (SLO: <30.000µs 📉 -19.2%) vs baseline: +1.0%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.1%

🟡 djangosimple - 30/30

✅ appsec

Time: ✅ 19.589ms (SLO: <22.300ms 📉 -12.2%) vs baseline: +0.3%

Memory: ✅ 68.223MB (SLO: <70.500MB -3.2%) vs baseline: +4.9%

✅ exception-replay-enabled

Time: ✅ 1.369ms (SLO: <1.450ms -5.6%) vs baseline: +0.6%

Memory: ✅ 66.265MB (SLO: <67.500MB 🟡 -1.8%) vs baseline: +4.8%

✅ iast

Time: ✅ 19.569ms (SLO: <22.250ms 📉 -12.0%) vs baseline: -0.4%

Memory: ✅ 68.203MB (SLO: <70.000MB -2.6%) vs baseline: +4.8%

✅ profiler

Time: ✅ 15.435ms (SLO: <16.550ms -6.7%) vs baseline: +0.1%

Memory: ✅ 56.398MB (SLO: <57.500MB 🟡 -1.9%) vs baseline: +5.0%

✅ resource-renaming

Time: ✅ 19.414ms (SLO: <21.750ms 📉 -10.7%) vs baseline: -0.5%

Memory: ✅ 68.125MB (SLO: <70.500MB -3.4%) vs baseline: +4.7%

✅ span-code-origin

Time: ✅ 20.011ms (SLO: <28.200ms 📉 -29.0%) vs baseline: +1.4%

Memory: ✅ 68.160MB (SLO: <71.000MB -4.0%) vs baseline: +4.9%

✅ tracer

Time: ✅ 19.611ms (SLO: <21.750ms -9.8%) vs baseline: ~same

Memory: ✅ 68.203MB (SLO: <70.000MB -2.6%) vs baseline: +4.9%

✅ tracer-and-profiler

Time: ✅ 21.717ms (SLO: <23.500ms -7.6%) vs baseline: -0.1%

Memory: ✅ 69.285MB (SLO: <71.000MB -2.4%) vs baseline: +4.9%

✅ tracer-dont-create-db-spans

Time: ✅ 19.675ms (SLO: <21.500ms -8.5%) vs baseline: +0.5%

Memory: ✅ 68.203MB (SLO: <70.000MB -2.6%) vs baseline: +4.8%

✅ tracer-minimal

Time: ✅ 16.786ms (SLO: <17.500ms -4.1%) vs baseline: +0.4%

Memory: ✅ 67.830MB (SLO: <70.000MB -3.1%) vs baseline: +4.9%

✅ tracer-native

Time: ✅ 19.412ms (SLO: <21.750ms 📉 -10.7%) vs baseline: -0.2%

Memory: ✅ 68.243MB (SLO: <72.500MB -5.9%) vs baseline: +4.8%

✅ tracer-no-caches

Time: ✅ 17.544ms (SLO: <19.650ms 📉 -10.7%) vs baseline: -0.5%

Memory: ✅ 67.830MB (SLO: <70.000MB -3.1%) vs baseline: +4.7%

✅ tracer-no-databases

Time: ✅ 19.124ms (SLO: <20.100ms -4.9%) vs baseline: +0.4%

Memory: ✅ 67.790MB (SLO: <70.000MB -3.2%) vs baseline: +4.9%

✅ tracer-no-middleware

Time: ✅ 19.275ms (SLO: <21.500ms 📉 -10.3%) vs baseline: -0.4%

Memory: ✅ 68.125MB (SLO: <70.000MB -2.7%) vs baseline: +5.0%

✅ tracer-no-templates

Time: ✅ 19.634ms (SLO: <22.000ms 📉 -10.8%) vs baseline: +1.5%

Memory: ✅ 68.174MB (SLO: <70.500MB -3.3%) vs baseline: +4.9%

🟡 errortrackingdjangosimple - 6/6

✅ errortracking-enabled-all

Time: ✅ 16.365ms (SLO: <19.850ms 📉 -17.6%) vs baseline: +0.7%

Memory: ✅ 69.816MB (SLO: <70.000MB 🟡 -0.3%) vs baseline: +4.9%

✅ errortracking-enabled-user

Time: ✅ 16.347ms (SLO: <19.400ms 📉 -15.7%) vs baseline: +0.3%

Memory: ✅ 69.855MB (SLO: <70.000MB 🟡 -0.2%) vs baseline: +5.0%

✅ tracer-enabled

Time: ✅ 16.267ms (SLO: <19.450ms 📉 -16.4%) vs baseline: -0.6%

Memory: ✅ 69.796MB (SLO: <70.000MB 🟡 -0.3%) vs baseline: +4.9%

🟡 errortrackingflasksqli - 6/6

✅ errortracking-enabled-all

Time: ✅ 2.068ms (SLO: <2.300ms 📉 -10.1%) vs baseline: +0.1%

Memory: ✅ 55.778MB (SLO: <56.500MB 🟡 -1.3%) vs baseline: +5.0%

✅ errortracking-enabled-user

Time: ✅ 2.074ms (SLO: <2.250ms -7.8%) vs baseline: ~same

Memory: ✅ 55.758MB (SLO: <56.500MB 🟡 -1.3%) vs baseline: +4.8%

✅ tracer-enabled

Time: ✅ 2.066ms (SLO: <2.300ms 📉 -10.2%) vs baseline: ~same

Memory: ✅ 55.679MB (SLO: <56.500MB 🟡 -1.5%) vs baseline: +4.9%

🟡 flasksimple - 18/18

✅ appsec-get

Time: ✅ 3.382ms (SLO: <4.750ms 📉 -28.8%) vs baseline: -0.4%

Memory: ✅ 55.484MB (SLO: <66.500MB 📉 -16.6%) vs baseline: +4.8%

✅ appsec-post

Time: ✅ 2.855ms (SLO: <6.750ms 📉 -57.7%) vs baseline: ~same

Memory: ✅ 55.445MB (SLO: <66.500MB 📉 -16.6%) vs baseline: +4.5%

✅ appsec-telemetry

Time: ✅ 3.417ms (SLO: <4.750ms 📉 -28.1%) vs baseline: +1.4%

Memory: ✅ 55.506MB (SLO: <66.500MB 📉 -16.5%) vs baseline: +4.8%

✅ debugger

Time: ✅ 1.871ms (SLO: <2.000ms -6.5%) vs baseline: +0.2%

Memory: ✅ 47.918MB (SLO: <49.500MB -3.2%) vs baseline: +4.9%

✅ iast-get

Time: ✅ 1.860ms (SLO: <2.000ms -7.0%) vs baseline: +0.2%

Memory: ✅ 44.555MB (SLO: <49.000MB -9.1%) vs baseline: +5.0%

✅ profiler

Time: ✅ 1.908ms (SLO: <2.100ms -9.2%) vs baseline: ~same

Memory: ✅ 48.879MB (SLO: <50.000MB -2.2%) vs baseline: +5.0%

✅ resource-renaming

Time: ✅ 3.367ms (SLO: <3.650ms -7.7%) vs baseline: +0.5%

Memory: ✅ 55.524MB (SLO: <56.000MB 🟡 -0.8%) vs baseline: +5.0%

✅ tracer

Time: ✅ 3.371ms (SLO: <3.650ms -7.7%) vs baseline: ~same

Memory: ✅ 55.485MB (SLO: <56.500MB 🟡 -1.8%) vs baseline: +4.8%

✅ tracer-native

Time: ✅ 3.361ms (SLO: <3.650ms -7.9%) vs baseline: -0.2%

Memory: ✅ 55.544MB (SLO: <60.000MB -7.4%) vs baseline: +4.9%

🟡 flasksqli - 6/6

✅ appsec-enabled

Time: ✅ 2.055ms (SLO: <4.200ms 📉 -51.1%) vs baseline: -0.1%

Memory: ✅ 55.737MB (SLO: <66.000MB 📉 -15.6%) vs baseline: +4.7%

✅ iast-enabled

Time: ✅ 2.068ms (SLO: <2.800ms 📉 -26.1%) vs baseline: ~same

Memory: ✅ 55.837MB (SLO: <62.500MB 📉 -10.7%) vs baseline: +5.0%

✅ tracer-enabled

Time: ✅ 2.055ms (SLO: <2.250ms -8.7%) vs baseline: -0.2%

Memory: ✅ 55.817MB (SLO: <56.500MB 🟡 -1.2%) vs baseline: +4.9%

🟡 httppropagationextract - 60/60

✅ all_styles_all_headers

Time: ✅ 81.164µs (SLO: <100.000µs 📉 -18.8%) vs baseline: +0.5%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.6%

✅ b3_headers

Time: ✅ 14.300µs (SLO: <20.000µs 📉 -28.5%) vs baseline: +1.7%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.6%

✅ b3_single_headers

Time: ✅ 13.328µs (SLO: <20.000µs 📉 -33.4%) vs baseline: -0.4%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ datadog_tracecontext_tracestate_not_propagated_on_trace_id_no_match

Time: ✅ 63.989µs (SLO: <80.000µs 📉 -20.0%) vs baseline: +0.6%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.9%

✅ datadog_tracecontext_tracestate_propagated_on_trace_id_match

Time: ✅ 69.549µs (SLO: <80.000µs 📉 -13.1%) vs baseline: +5.5%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.5%

✅ empty_headers

Time: ✅ 1.623µs (SLO: <10.000µs 📉 -83.8%) vs baseline: +0.2%

Memory: ✅ 34.918MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +4.8%

✅ full_t_id_datadog_headers

Time: ✅ 22.601µs (SLO: <30.000µs 📉 -24.7%) vs baseline: +0.8%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.4%

✅ invalid_priority_header

Time: ✅ 6.518µs (SLO: <10.000µs 📉 -34.8%) vs baseline: +0.4%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.9%

✅ invalid_span_id_header

Time: ✅ 6.491µs (SLO: <10.000µs 📉 -35.1%) vs baseline: -0.7%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ invalid_tags_header

Time: ✅ 6.515µs (SLO: <10.000µs 📉 -34.9%) vs baseline: ~same

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.9%

✅ invalid_trace_id_header

Time: ✅ 6.541µs (SLO: <10.000µs 📉 -34.6%) vs baseline: +0.2%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.7%

✅ large_header_no_matches

Time: ✅ 27.679µs (SLO: <30.000µs -7.7%) vs baseline: +0.4%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +5.0%

✅ large_valid_headers_all

Time: ✅ 28.669µs (SLO: <40.000µs 📉 -28.3%) vs baseline: ~same

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.8%

✅ medium_header_no_matches

Time: ✅ 9.862µs (SLO: <20.000µs 📉 -50.7%) vs baseline: -0.2%

Memory: ✅ 34.898MB (SLO: <35.500MB 🟡 -1.7%) vs baseline: +5.0%

✅ medium_valid_headers_all

Time: ✅ 11.324µs (SLO: <20.000µs 📉 -43.4%) vs baseline: +0.1%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.1%

✅ none_propagation_style

Time: ✅ 1.715µs (SLO: <10.000µs 📉 -82.9%) vs baseline: -0.2%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.5%

✅ tracecontext_headers

Time: ✅ 35.071µs (SLO: <40.000µs 📉 -12.3%) vs baseline: +1.0%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.6%

✅ valid_headers_all

Time: ✅ 6.523µs (SLO: <10.000µs 📉 -34.8%) vs baseline: +0.5%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.7%

✅ valid_headers_basic

Time: ✅ 6.082µs (SLO: <10.000µs 📉 -39.2%) vs baseline: -0.6%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ wsgi_empty_headers

Time: ✅ 1.612µs (SLO: <10.000µs 📉 -83.9%) vs baseline: -0.4%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ wsgi_invalid_priority_header

Time: ✅ 6.567µs (SLO: <10.000µs 📉 -34.3%) vs baseline: +0.3%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.7%

✅ wsgi_invalid_span_id_header

Time: ✅ 1.608µs (SLO: <10.000µs 📉 -83.9%) vs baseline: ~same

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.9%

✅ wsgi_invalid_tags_header

Time: ✅ 6.576µs (SLO: <10.000µs 📉 -34.2%) vs baseline: -0.2%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +4.8%

✅ wsgi_invalid_trace_id_header

Time: ✅ 6.635µs (SLO: <10.000µs 📉 -33.6%) vs baseline: +1.1%

Memory: ✅ 34.918MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +5.0%

✅ wsgi_large_header_no_matches

Time: ✅ 28.665µs (SLO: <40.000µs 📉 -28.3%) vs baseline: -0.3%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ wsgi_large_valid_headers_all

Time: ✅ 29.982µs (SLO: <40.000µs 📉 -25.0%) vs baseline: +0.9%

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +4.3%

✅ wsgi_medium_header_no_matches

Time: ✅ 10.140µs (SLO: <20.000µs 📉 -49.3%) vs baseline: +0.5%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.5%

✅ wsgi_medium_valid_headers_all

Time: ✅ 11.567µs (SLO: <20.000µs 📉 -42.2%) vs baseline: +0.5%

Memory: ✅ 34.937MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +5.0%

✅ wsgi_valid_headers_all

Time: ✅ 6.557µs (SLO: <10.000µs 📉 -34.4%) vs baseline: -0.7%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.9%

✅ wsgi_valid_headers_basic

Time: ✅ 6.116µs (SLO: <10.000µs 📉 -38.8%) vs baseline: -0.4%

Memory: ✅ 34.937MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +5.3%

🟡 httppropagationinject - 16/16

✅ ids_only

Time: ✅ 22.099µs (SLO: <30.000µs 📉 -26.3%) vs baseline: +5.1%

Memory: ✅ 34.859MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

✅ with_all

Time: ✅ 27.893µs (SLO: <40.000µs 📉 -30.3%) vs baseline: +0.3%

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +4.6%

✅ with_dd_origin

Time: ✅ 24.795µs (SLO: <30.000µs 📉 -17.3%) vs baseline: +0.1%

Memory: ✅ 34.800MB (SLO: <35.500MB 🟡 -2.0%) vs baseline: +4.8%

✅ with_priority_and_origin

Time: ✅ 24.357µs (SLO: <40.000µs 📉 -39.1%) vs baseline: +0.4%

Memory: ✅ 34.918MB (SLO: <35.500MB 🟡 -1.6%) vs baseline: +5.3%

✅ with_sampling_priority

Time: ✅ 21.034µs (SLO: <30.000µs 📉 -29.9%) vs baseline: ~same

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.6%

✅ with_tags

Time: ✅ 25.868µs (SLO: <40.000µs 📉 -35.3%) vs baseline: ~same

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.9%

✅ with_tags_invalid

Time: ✅ 27.402µs (SLO: <40.000µs 📉 -31.5%) vs baseline: +0.7%

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +4.7%

✅ with_tags_max_size

Time: ✅ 26.437µs (SLO: <40.000µs 📉 -33.9%) vs baseline: +0.5%

Memory: ✅ 34.878MB (SLO: <35.500MB 🟡 -1.8%) vs baseline: +5.0%

🟡 iast_aspects - 40/40

✅ re_expand_aspect

Time: ✅ 34.192µs (SLO: <40.000µs 📉 -14.5%) vs baseline: +7.7%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +5.1%

✅ re_expand_noaspect

Time: ✅ 28.714µs (SLO: <40.000µs 📉 -28.2%) vs baseline: -0.2%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.7%

✅ re_findall_aspect

Time: ✅ 2.932µs (SLO: <10.000µs 📉 -70.7%) vs baseline: -0.1%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +5.2%

✅ re_findall_noaspect

Time: ✅ 1.416µs (SLO: <10.000µs 📉 -85.8%) vs baseline: +0.2%

Memory: ✅ 40.128MB (SLO: <41.000MB -2.1%) vs baseline: +4.9%

✅ re_finditer_aspect

Time: ✅ 4.452µs (SLO: <10.000µs 📉 -55.5%) vs baseline: -0.5%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.9%

✅ re_finditer_noaspect

Time: ✅ 1.417µs (SLO: <10.000µs 📉 -85.8%) vs baseline: +0.3%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.9%

✅ re_fullmatch_aspect

Time: ✅ 2.738µs (SLO: <10.000µs 📉 -72.6%) vs baseline: +0.9%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +5.2%

✅ re_fullmatch_noaspect

Time: ✅ 1.316µs (SLO: <10.000µs 📉 -86.8%) vs baseline: -1.3%

Memory: ✅ 40.246MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.9%

✅ re_group_aspect

Time: ✅ 3.008µs (SLO: <10.000µs 📉 -69.9%) vs baseline: -0.3%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.8%

✅ re_group_noaspect

Time: ✅ 1.627µs (SLO: <10.000µs 📉 -83.7%) vs baseline: +0.1%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +4.8%

✅ re_groups_aspect

Time: ✅ 3.141µs (SLO: <10.000µs 📉 -68.6%) vs baseline: +0.3%

Memory: ✅ 40.305MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.3%

✅ re_groups_noaspect

Time: ✅ 1.702µs (SLO: <10.000µs 📉 -83.0%) vs baseline: -1.7%

Memory: ✅ 40.147MB (SLO: <41.000MB -2.1%) vs baseline: +4.8%

✅ re_match_aspect

Time: ✅ 2.765µs (SLO: <10.000µs 📉 -72.3%) vs baseline: -1.1%

Memory: ✅ 40.147MB (SLO: <41.000MB -2.1%) vs baseline: +4.7%

✅ re_match_noaspect

Time: ✅ 1.306µs (SLO: <10.000µs 📉 -86.9%) vs baseline: -1.8%

Memory: ✅ 40.187MB (SLO: <41.000MB 🟡 -2.0%) vs baseline: +4.7%

✅ re_search_aspect

Time: ✅ 2.579µs (SLO: <10.000µs 📉 -74.2%) vs baseline: +0.5%

Memory: ✅ 40.265MB (SLO: <41.000MB 🟡 -1.8%) vs baseline: +4.8%

✅ re_search_noaspect

Time: ✅ 1.198µs (SLO: <10.000µs 📉 -88.0%) vs baseline: -1.6%

Memory: ✅ 40.147MB (SLO: <41.000MB -2.1%) vs baseline: +4.6%

✅ re_sub_aspect

Time: ✅ 3.596µs (SLO: <10.000µs 📉 -64.0%) vs baseline: +4.5%

Memory: ✅ 40.226MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.6%

✅ re_sub_noaspect

Time: ✅ 1.537µs (SLO: <10.000µs 📉 -84.6%) vs baseline: -0.1%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +5.1%

✅ re_subn_aspect

Time: ✅ 3.671µs (SLO: <10.000µs 📉 -63.3%) vs baseline: -0.7%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +4.9%

✅ re_subn_noaspect

Time: ✅ 1.618µs (SLO: <10.000µs 📉 -83.8%) vs baseline: ~same

Memory: ✅ 40.187MB (SLO: <41.000MB 🟡 -2.0%) vs baseline: +4.7%

🟡 iastaspectssplit - 12/12

✅ rsplit_aspect

Time: ✅ 1.543µs (SLO: <10.000µs 📉 -84.6%) vs baseline: +5.9%

Memory: ✅ 39.990MB (SLO: <41.000MB -2.5%) vs baseline: +4.2%

✅ rsplit_noaspect

Time: ✅ 0.574µs (SLO: <10.000µs 📉 -94.3%) vs baseline: -1.7%

Memory: ✅ 40.206MB (SLO: <41.000MB 🟡 -1.9%) vs baseline: +4.6%

✅ split_aspect

Time: ✅ 1.438µs (SLO: <10.000µs 📉 -85.6%) vs baseline: +1.6%

Memory: ✅ 40.285MB (SLO: <41.000MB 🟡 -1.7%) vs baseline: +4.7%

✅ split_noaspect

Time: ✅ 0.572µs (SLO: <10.000µs 📉 -94.3%) vs baseline: -0.2%

Memory: ✅ 40.187MB (SLO: <41.000MB 🟡 -2.0%) vs baseline: +4.6%

✅ splitlines_aspect

Time: ✅ 1.418µs (SLO: <10.000µs 📉 -85.8%) vs baseline: +0.6%

Memory: ✅ 40.128MB (SLO: <41.000MB -2.1%) vs baseline: +4.6%

✅ splitlines_noaspect

Time: ✅ 0.583µs (SLO: <10.000µs 📉 -94.2%) vs baseline: -0.4%

Memory: ✅ 40.029MB (SLO: <41.000MB -2.4%) vs baseline: +4.2%

🟡 otelspan - 22/22

✅ add-event

Time: ✅ 40.490ms (SLO: <47.150ms 📉 -14.1%) vs baseline: +2.4%

Memory: ✅ 39.521MB (SLO: <47.000MB 📉 -15.9%) vs baseline: +4.9%

✅ add-metrics

Time: ✅ 263.297ms (SLO: <344.800ms 📉 -23.6%) vs baseline: +0.9%

Memory: ✅ 43.658MB (SLO: <47.500MB -8.1%) vs baseline: +4.3%

✅ add-tags

Time: ✅ 316.757ms (SLO: <321.000ms 🟡 -1.3%) vs baseline: -0.4%

Memory: ✅ 43.817MB (SLO: <47.500MB -7.8%) vs baseline: +5.0%

✅ get-context

Time: ✅ 80.405ms (SLO: <92.350ms 📉 -12.9%) vs baseline: +0.7%

Memory: ✅ 39.901MB (SLO: <46.500MB 📉 -14.2%) vs baseline: +5.7%

✅ is-recording

Time: ✅ 37.977ms (SLO: <44.500ms 📉 -14.7%) vs baseline: +2.3%

Memory: ✅ 39.489MB (SLO: <47.500MB 📉 -16.9%) vs baseline: +4.5%

✅ record-exception

Time: ✅ 58.974ms (SLO: <67.650ms 📉 -12.8%) vs baseline: +1.3%

Memory: ✅ 39.923MB (SLO: <47.000MB 📉 -15.1%) vs baseline: +4.8%

✅ set-status

Time: ✅ 44.418ms (SLO: <50.400ms 📉 -11.9%) vs baseline: +1.2%

Memory: ✅ 39.378MB (SLO: <47.000MB 📉 -16.2%) vs baseline: +4.5%

✅ start

Time: ✅ 38.137ms (SLO: <43.450ms 📉 -12.2%) vs baseline: +4.1%

Memory: ✅ 39.624MB (SLO: <47.000MB 📉 -15.7%) vs baseline: +4.7%

✅ start-finish

Time: ✅ 82.637ms (SLO: <88.000ms -6.1%) vs baseline: +0.9%

Memory: ✅ 37.356MB (SLO: <46.500MB 📉 -19.7%) vs baseline: +4.9%

✅ start-finish-telemetry

Time: ✅ 84.141ms (SLO: <89.000ms -5.5%) vs baseline: +0.8%

Memory: ✅ 37.336MB (SLO: <46.500MB 📉 -19.7%) vs baseline: +4.8%

✅ update-name

Time: ✅ 38.752ms (SLO: <45.150ms 📉 -14.2%) vs baseline: +1.5%

Memory: ✅ 39.600MB (SLO: <47.000MB 📉 -15.7%) vs baseline: +4.5%

🟡 packagespackageforrootmodulemapping - 4/4

✅ cache_off

Time: ✅ 342.847ms (SLO: <354.300ms -3.2%) vs baseline: -0.9%

Memory: ✅ 40.674MB (SLO: <41.500MB 🟡 -2.0%) vs baseline: +4.4%

✅ cache_on

Time: ✅ 0.384µs (SLO: <10.000µs 📉 -96.2%) vs baseline: +0.4%

Memory: ✅ 40.074MB (SLO: <41.000MB -2.3%) vs baseline: +4.2%

🟡 ratelimiter - 12/12

✅ defaults

Time: ✅ 2.352µs (SLO: <10.000µs 📉 -76.5%) vs baseline: ~same

Memory: ✅ 34.780MB (SLO: <35.500MB -2.0%) vs baseline: +3.6%

✅ high_rate_limit

Time: ✅ 2.433µs (SLO: <10.000µs 📉 -75.7%) vs baseline: +0.5%

Memory: ✅ 35.036MB (SLO: <35.500MB 🟡 -1.3%) vs baseline: +4.8%

✅ long_window

Time: ✅ 2.364µs (SLO: <10.000µs 📉 -76.4%) vs baseline: ~same

Memory: ✅ 35.095MB (SLO: <35.500MB 🟡 -1.1%) vs baseline: +5.0%

✅ low_rate_limit

Time: ✅ 2.359µs (SLO: <10.000µs 📉 -76.4%) vs baseline: ~same

Memory: ✅ 35.134MB (SLO: <35.500MB 🟡 -1.0%) vs baseline: +4.9%

✅ no_rate_limit

Time: ✅ 0.826µs (SLO: <10.000µs 📉 -91.7%) vs baseline: ~same

Memory: ✅ 35.154MB (SLO: <35.500MB 🟡 -1.0%) vs baseline: +5.3%

✅ short_window

Time: ✅ 2.480µs (SLO: <10.000µs 📉 -75.2%) vs baseline: -0.2%

Memory: ✅ 35.075MB (SLO: <35.500MB 🟡 -1.2%) vs baseline: +4.8%

🟡 recursivecomputation - 8/8

✅ deep

Time: ✅ 308.725ms (SLO: <320.950ms -3.8%) vs baseline: +0.1%

Memory: ✅ 35.861MB (SLO: <36.500MB 🟡 -1.7%) vs baseline: +4.7%

✅ deep-profiled

Time: ✅ 328.047ms (SLO: <359.150ms -8.7%) vs baseline: ~same

Memory: ✅ 39.793MB (SLO: <40.500MB 🟡 -1.7%) vs baseline: +4.6%

✅ medium

Time: ✅ 6.995ms (SLO: <7.400ms -5.5%) vs baseline: +0.3%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.7%

✅ shallow

Time: ✅ 0.949ms (SLO: <1.050ms -9.7%) vs baseline: +1.4%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.2%

🟡 sethttpmeta - 32/32

✅ all-disabled

Time: ✅ 10.619µs (SLO: <20.000µs 📉 -46.9%) vs baseline: +0.9%

Memory: ✅ 35.645MB (SLO: <36.000MB 🟡 -1.0%) vs baseline: +4.6%

✅ all-enabled

Time: ✅ 41.107µs (SLO: <50.000µs 📉 -17.8%) vs baseline: +2.3%

Memory: ✅ 35.527MB (SLO: <36.000MB 🟡 -1.3%) vs baseline: +4.7%

✅ collectipvariant_exists

Time: ✅ 40.887µs (SLO: <50.000µs 📉 -18.2%) vs baseline: -0.4%

Memory: ✅ 35.645MB (SLO: <36.000MB 🟡 -1.0%) vs baseline: +4.9%

✅ no-collectipvariant

Time: ✅ 40.309µs (SLO: <50.000µs 📉 -19.4%) vs baseline: +0.3%

Memory: ✅ 35.547MB (SLO: <36.000MB 🟡 -1.3%) vs baseline: +4.9%

✅ no-useragentvariant

Time: ✅ 39.048µs (SLO: <50.000µs 📉 -21.9%) vs baseline: +0.6%

Memory: ✅ 35.429MB (SLO: <36.000MB 🟡 -1.6%) vs baseline: +3.9%

✅ obfuscation-no-query

Time: ✅ 40.823µs (SLO: <50.000µs 📉 -18.4%) vs baseline: +0.3%

Memory: ✅ 35.507MB (SLO: <36.000MB 🟡 -1.4%) vs baseline: +5.6%

✅ obfuscation-regular-case-explicit-query

Time: ✅ 75.910µs (SLO: <90.000µs 📉 -15.7%) vs baseline: +0.4%

Memory: ✅ 35.527MB (SLO: <36.500MB -2.7%) vs baseline: +4.7%

✅ obfuscation-regular-case-implicit-query

Time: ✅ 76.440µs (SLO: <90.000µs 📉 -15.1%) vs baseline: ~same

Memory: ✅ 35.606MB (SLO: <36.500MB -2.5%) vs baseline: +4.7%

✅ obfuscation-send-querystring-disabled

Time: ✅ 154.625µs (SLO: <170.000µs -9.0%) vs baseline: +0.2%

Memory: ✅ 35.763MB (SLO: <36.500MB -2.0%) vs baseline: +5.1%

✅ obfuscation-worst-case-explicit-query

Time: ✅ 148.934µs (SLO: <160.000µs -6.9%) vs baseline: +0.3%

Memory: ✅ 35.783MB (SLO: <36.500MB 🟡 -2.0%) vs baseline: +5.1%

✅ obfuscation-worst-case-implicit-query

Time: ✅ 155.380µs (SLO: <170.000µs -8.6%) vs baseline: +0.1%

Memory: ✅ 35.684MB (SLO: <36.500MB -2.2%) vs baseline: +5.0%

✅ useragentvariant_exists_1

Time: ✅ 39.854µs (SLO: <50.000µs 📉 -20.3%) vs baseline: +1.1%

Memory: ✅ 35.350MB (SLO: <36.000MB 🟡 -1.8%) vs baseline: +4.7%

✅ useragentvariant_exists_2

Time: ✅ 40.848µs (SLO: <50.000µs 📉 -18.3%) vs baseline: ~same

Memory: ✅ 35.271MB (SLO: <36.000MB -2.0%) vs baseline: +3.8%

✅ useragentvariant_exists_3

Time: ✅ 40.191µs (SLO: <50.000µs 📉 -19.6%) vs baseline: -0.3%

Memory: ✅ 35.370MB (SLO: <36.000MB 🟡 -1.8%) vs baseline: +4.2%

✅ useragentvariant_not_exists_1

Time: ✅ 39.738µs (SLO: <50.000µs 📉 -20.5%) vs baseline: +0.3%

Memory: ✅ 35.645MB (SLO: <36.000MB 🟡 -1.0%) vs baseline: +5.0%

✅ useragentvariant_not_exists_2

Time: ✅ 39.703µs (SLO: <50.000µs 📉 -20.6%) vs baseline: +0.4%

Memory: ✅ 35.488MB (SLO: <36.000MB 🟡 -1.4%) vs baseline: +4.2%

🟡 span - 26/26

✅ add-event

Time: ✅ 18.294ms (SLO: <22.500ms 📉 -18.7%) vs baseline: +0.3%

Memory: ✅ 36.765MB (SLO: <53.000MB 📉 -30.6%) vs baseline: +4.2%

✅ add-metrics

Time: ✅ 87.957ms (SLO: <93.500ms -5.9%) vs baseline: -0.7%

Memory: ✅ 41.105MB (SLO: <53.000MB 📉 -22.4%) vs baseline: +4.9%

✅ add-tags

Time: ✅ 142.559ms (SLO: <155.000ms -8.0%) vs baseline: +0.6%

Memory: ✅ 41.127MB (SLO: <53.000MB 📉 -22.4%) vs baseline: +5.1%

✅ get-context

Time: ✅ 17.060ms (SLO: <20.500ms 📉 -16.8%) vs baseline: +0.3%

Memory: ✅ 36.745MB (SLO: <53.000MB 📉 -30.7%) vs baseline: +5.0%

✅ is-recording

Time: ✅ 17.258ms (SLO: <20.500ms 📉 -15.8%) vs baseline: -0.6%

Memory: ✅ 36.739MB (SLO: <53.000MB 📉 -30.7%) vs baseline: +4.9%

✅ record-exception

Time: ✅ 36.859ms (SLO: <40.000ms -7.9%) vs baseline: +1.0%

Memory: ✅ 37.282MB (SLO: <53.000MB 📉 -29.7%) vs baseline: +4.9%

✅ set-status

Time: ✅ 18.800ms (SLO: <22.000ms 📉 -14.5%) vs baseline: +0.4%

Memory: ✅ 36.815MB (SLO: <53.000MB 📉 -30.5%) vs baseline: +5.3%

✅ start

Time: ✅ 17.410ms (SLO: <20.500ms 📉 -15.1%) vs baseline: +2.7%

Memory: ✅ 36.722MB (SLO: <53.000MB 📉 -30.7%) vs baseline: +4.9%

✅ start-finish

Time: ✅ 51.106ms (SLO: <52.500ms -2.7%) vs baseline: ~same

Memory: ✅ 34.760MB (SLO: <35.500MB -2.1%) vs baseline: +5.0%

✅ start-finish-telemetry

Time: ✅ 52.204ms (SLO: <54.500ms -4.2%) vs baseline: -0.6%

Memory: ✅ 34.839MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.0%

✅ start-finish-traceid128

Time: ✅ 54.055ms (SLO: <57.000ms -5.2%) vs baseline: -0.6%

Memory: ✅ 34.701MB (SLO: <35.500MB -2.2%) vs baseline: +4.3%

✅ start-traceid128

Time: ✅ 17.248ms (SLO: <22.500ms 📉 -23.3%) vs baseline: ~same

Memory: ✅ 36.703MB (SLO: <53.000MB 📉 -30.7%) vs baseline: +5.0%

✅ update-name

Time: ✅ 17.257ms (SLO: <22.000ms 📉 -21.6%) vs baseline: -0.6%

Memory: ✅ 36.799MB (SLO: <53.000MB 📉 -30.6%) vs baseline: +4.7%

🟡 tracer - 6/6

✅ large

Time: ✅ 29.247ms (SLO: <32.950ms 📉 -11.2%) vs baseline: -0.3%

Memory: ✅ 35.881MB (SLO: <36.500MB 🟡 -1.7%) vs baseline: +4.9%

✅ medium

Time: ✅ 2.890ms (SLO: <3.200ms -9.7%) vs baseline: +0.5%

Memory: ✅ 34.741MB (SLO: <35.500MB -2.1%) vs baseline: +4.6%

✅ small

Time: ✅ 331.874µs (SLO: <370.000µs 📉 -10.3%) vs baseline: +1.8%

Memory: ✅ 34.819MB (SLO: <35.500MB 🟡 -1.9%) vs baseline: +5.2%

⚠️ Unstable Tests (1 suite)
⚠️ packagesupdateimporteddependencies - 24/24 (1 unstable)

✅ import_many

Time: ✅ 154.643µs (SLO: <170.000µs -9.0%) vs baseline: -0.1%

Memory: ✅ 39.437MB (SLO: <41.000MB -3.8%) vs baseline: +4.2%

✅ import_many_cached

Time: ✅ 120.983µs (SLO: <130.000µs -6.9%) vs baseline: -0.7%

Memory: ✅ 39.562MB (SLO: <41.000MB -3.5%) vs baseline: +4.4%

✅ import_many_stdlib

Time: ✅ 0.753ms (SLO: <1.750ms 📉 -57.0%) vs baseline: -0.4%

Memory: ✅ 39.541MB (SLO: <41.000MB -3.6%) vs baseline: +4.9%

⚠️ import_many_stdlib_cached

Time: ⚠️ 0.172ms (SLO: <1.100ms 📉 -84.4%) vs baseline: -0.6%

Memory: ✅ 39.512MB (SLO: <41.000MB -3.6%) vs baseline: +4.1%

✅ import_many_unknown

Time: ✅ 835.434µs (SLO: <890.000µs -6.1%) vs baseline: +0.1%

Memory: ✅ 39.822MB (SLO: <41.000MB -2.9%) vs baseline: +5.7%

✅ import_many_unknown_cached

Time: ✅ 788.426µs (SLO: <870.000µs -9.4%) vs baseline: -0.4%

Memory: ✅ 39.747MB (SLO: <41.000MB -3.1%) vs baseline: +5.1%

✅ import_one

Time: ✅ 19.633µs (SLO: <30.000µs 📉 -34.6%) vs baseline: -1.1%

Memory: ✅ 39.520MB (SLO: <41.000MB -3.6%) vs baseline: +4.7%

✅ import_one_cache

Time: ✅ 6.232µs (SLO: <10.000µs 📉 -37.7%) vs baseline: -0.7%

Memory: ✅ 39.556MB (SLO: <41.000MB -3.5%) vs baseline: +4.6%

✅ import_one_stdlib

Time: ✅ 18.671µs (SLO: <20.000µs -6.6%) vs baseline: ~same

Memory: ✅ 39.529MB (SLO: <41.000MB -3.6%) vs baseline: +4.5%

✅ import_one_stdlib_cache

Time: ✅ 6.281µs (SLO: <10.000µs 📉 -37.2%) vs baseline: +0.1%

Memory: ✅ 39.520MB (SLO: <41.000MB -3.6%) vs baseline: +4.5%

✅ import_one_unknown

Time: ✅ 45.228µs (SLO: <50.000µs -9.5%) vs baseline: ~same

Memory: ✅ 40.040MB (SLO: <41.000MB -2.3%) vs baseline: +6.5%

✅ import_one_unknown_cache

Time: ✅ 6.277µs (SLO: <10.000µs 📉 -37.2%) vs baseline: -0.4%

Memory: ✅ 39.560MB (SLO: <41.000MB -3.5%) vs baseline: +4.7%

✅ All Tests Passing (3 suites)
✅ iastpropagation - 8/8

✅ no-propagation

Time: ✅ 48.632µs (SLO: <60.000µs 📉 -18.9%) vs baseline: -0.2%

Memory: ✅ 40.128MB (SLO: <42.000MB -4.5%) vs baseline: +4.9%

✅ propagation_enabled

Time: ✅ 175.534µs (SLO: <190.000µs -7.6%) vs baseline: +0.5%

Memory: ✅ 40.167MB (SLO: <42.000MB -4.4%) vs baseline: +5.1%

✅ propagation_enabled_100

Time: ✅ 1.953ms (SLO: <2.300ms 📉 -15.1%) vs baseline: +1.1%

Memory: ✅ 40.049MB (SLO: <42.000MB -4.6%) vs baseline: +4.7%

✅ propagation_enabled_1000

Time: ✅ 32.559ms (SLO: <34.550ms -5.8%) vs baseline: +0.3%

Memory: ✅ 40.088MB (SLO: <42.000MB -4.6%) vs baseline: +4.8%

✅ otelsdkspan - 24/24

✅ add-event

Time: ✅ 40.431ms (SLO: <42.000ms -3.7%) vs baseline: ~same

Memory: ✅ 37.631MB (SLO: <39.000MB -3.5%) vs baseline: +4.8%

✅ add-link

Time: ✅ 36.399ms (SLO: <38.550ms -5.6%) vs baseline: +0.5%

Memory: ✅ 37.650MB (SLO: <39.000MB -3.5%) vs baseline: +5.0%

✅ add-metrics

Time: ✅ 219.284ms (SLO: <232.000ms -5.5%) vs baseline: +0.4%

Memory: ✅ 37.591MB (SLO: <39.000MB -3.6%) vs baseline: +4.9%

✅ add-tags

Time: ✅ 211.408ms (SLO: <221.600ms -4.6%) vs baseline: +0.5%

Memory: ✅ 37.709MB (SLO: <39.000MB -3.3%) vs baseline: +5.1%

✅ get-context

Time: ✅ 29.271ms (SLO: <31.300ms -6.5%) vs baseline: +0.5%

Memory: ✅ 37.650MB (SLO: <39.000MB -3.5%) vs baseline: +4.7%

✅ is-recording

Time: ✅ 29.240ms (SLO: <31.000ms -5.7%) vs baseline: -0.5%

Memory: ✅ 37.591MB (SLO: <39.000MB -3.6%) vs baseline: +4.5%

✅ record-exception

Time: ✅ 62.953ms (SLO: <65.850ms -4.4%) vs baseline: -0.4%

Memory: ✅ 37.690MB (SLO: <39.000MB -3.4%) vs baseline: +5.1%

✅ set-status

Time: ✅ 32.255ms (SLO: <34.150ms -5.5%) vs baseline: +0.7%

Memory: ✅ 37.650MB (SLO: <39.000MB -3.5%) vs baseline: +4.7%

✅ start

Time: ✅ 29.438ms (SLO: <30.150ms -2.4%) vs baseline: +2.0%

Memory: ✅ 37.513MB (SLO: <39.000MB -3.8%) vs baseline: +4.4%

✅ start-finish

Time: ✅ 34.047ms (SLO: <35.350ms -3.7%) vs baseline: +0.2%

Memory: ✅ 37.690MB (SLO: <39.000MB -3.4%) vs baseline: +5.1%

✅ start-finish-telemetry

Time: ✅ 34.204ms (SLO: <35.450ms -3.5%) vs baseline: +0.5%

Memory: ✅ 37.690MB (SLO: <39.000MB -3.4%) vs baseline: +5.1%

✅ update-name

Time: ✅ 31.349ms (SLO: <33.400ms -6.1%) vs baseline: +0.8%

Memory: ✅ 37.670MB (SLO: <39.000MB -3.4%) vs baseline: +4.8%

✅ samplingrules - 8/8

✅ average_match

Time: ✅ 137.211µs (SLO: <290.000µs 📉 -52.7%) vs baseline: +0.4%

Memory: ✅ 34.682MB (SLO: <35.500MB -2.3%) vs baseline: +4.6%

✅ high_match

Time: ✅ 173.420µs (SLO: <480.000µs 📉 -63.9%) vs baseline: ~same

Memory: ✅ 34.642MB (SLO: <35.500MB -2.4%) vs baseline: +4.7%

✅ low_match

Time: ✅ 99.046µs (SLO: <120.000µs 📉 -17.5%) vs baseline: ~same

Memory: ✅ 603.510MB (SLO: <700.000MB 📉 -13.8%) vs baseline: +4.9%

✅ very_low_match

Time: ✅ 2.652ms (SLO: <8.500ms 📉 -68.8%) vs baseline: +0.2%

Memory: ✅ 71.067MB (SLO: <75.000MB -5.2%) vs baseline: +5.0%

ℹ️ Scenarios Missing SLO Configuration (10 scenarios)

The following scenarios exist in candidate data but have no SLO thresholds configured:

  • coreapiscenario-core_dispatch_listeners
  • coreapiscenario-core_dispatch_no_listeners
  • coreapiscenario-core_dispatch_with_results_listeners
  • coreapiscenario-core_dispatch_with_results_no_listeners
  • djangosimple-baseline
  • errortrackingdjangosimple-baseline
  • errortrackingflasksqli-baseline
  • flasksimple-baseline
  • flasksqli-baseline
  • sethttpmeta-obfuscation-disabled

@KowalskiThomas
Copy link
Contributor Author

KowalskiThomas commented Dec 8, 2025

I'll double Check, but this fixes an edge case that is already covered by a test (that was a bit flaky, at least in echion, due to this race condition). I'll double check and try to add a test that triggers the issue in a sure fire way.

@KowalskiThomas
Copy link
Contributor Author

KowalskiThomas commented Dec 8, 2025

@taegyunkim I double checked and the test that was spuriously failing in Echion due to this race condition seems not to flake (see here) in dd-trace-py, potentially due to our lower sampling rate. If you look at the CI history in the Echion repo, though, you will easily find instances of the test for asyncio.as_completed failing – that is because certain of the 10 Tasks we create were being wiped out.

@KowalskiThomas KowalskiThomas force-pushed the kowalski/fix-profiling-do-not-remove-links-for-just-created-tasks branch from 5b8add2 to eba6d01 Compare December 9, 2025 09:07
@KowalskiThomas
Copy link
Contributor Author

KowalskiThomas commented Dec 9, 2025 •
edited
Loading

@taegyunkim I just had another look to the test and it seems like the one we had in dd-trace-py was much more basic than the one in Echion – probably due to its tendency to flake. I updated it (in the current PR) to be the same as Echion – many Tasks, and we check that we've seen what we expect in all Tasks [except for 1, as we have a known issue in dd-trace-py that makes one of the Tasks appear as part of the Parent Task]

I wouldn't have realised this without your comment – thanks for calling it out! 🙇

@KowalskiThomas KowalskiThomas force-pushed the kowalski/fix-profiling-do-not-remove-links-for-just-created-tasks branch from eba6d01 to a7baa36 Compare December 9, 2025 09:12
This was referenced Dec 9, 2025
Merged
Merged
taegyunkim
taegyunkim approved these changes Dec 9, 2025
View reviewed changes
Copy link
Contributor

@taegyunkim taegyunkim left a comment

Choose a reason for hiding this comment

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

Thanks for updating the test!

@KowalskiThomas KowalskiThomas merged commit 09066c3 into main Dec 9, 2025
445 checks passed
@KowalskiThomas KowalskiThomas deleted the kowalski/fix-profiling-do-not-remove-links-for-just-created-tasks branch December 9, 2025 14:42
@KowalskiThomas KowalskiThomas mentioned this pull request Dec 9, 2025
Merged
KowalskiThomas added a commit that referenced this pull request Dec 11, 2025
@KowalskiThomas
fix(profiling): correctly unwind on-CPU Tasks (#15562)
affc3c7 
## What does this PR do?

More details and investigation results available in
https://datadoghq.atlassian.net/browse/PROF-13137

Related PRs
* Dependency: #15552
* Dependent: #15579
* Echion PR: P403n1x87/echion#198

This PR fixes the way we sample and capture stacks for on-CPU asyncio
Tasks. This is a first step towards fixing _all_ weird (sub-)stacks we
are seeing (both in Echion and dd-trace-py), for example this one...

```
background_math_function
Task-background_wait
background_wait_function
sleep
```

... where in practice, `background_math_function` was executed as part
of a Task that was completely unrelated to `Task-background_wait` and
should never have appeared in the same stack.

This by itself doesn't fix everything (see **The fix(es, actually)**),
but, as I said, it's a first step.

See [this
document](https://docs.google.com/document/d/10HmKhY6tM5j7ojdk7CG8anWsN7qP7IyeZlj3-zAXudM/edit?pli=1&tab=t.9pzrl0uli4g)
for more explanations around how this works / is supposed to work, the
fix is explained at the bottom here.

## The fix(es, actually)

### Flawed existing logic...

The fix logic is the following:
* To correctly interleave Task Stacks and Task names, we need to
determine the "synchronous Python top-of-stack" that goes on top of the
on-CPU Task (if there is an on-CPU Task).
* This includes the Python stack that eventually led to doing something
like `asyncio.run`, as well as the internal `asyncio` Runner machinery.
* We will have to push this on top of every Task Stack we capture (note
that the on-CPU Stack will already have it by definition).
* To do that, we need to determine which Task is "the on CPU Task" (if
any) and process it first, so that we know how "high" the "upper Python
stack" is and we can re-use it for subsequent Task unwindings.
* To ensure the first Task we unwind is the on-CPU one, we first sort
the Leaf Tasks array by on-CPU-ness
* Note I'm saying _the_ on CPU Task because, as always in Python, there
can only be one thing running at a time.
* (Well, that's the case at least in theory – in practice on-CPU-ness
may change as we sample and so we could end up with more than one on-CPU
Task, but that is fine because it won't change how deep the "upper
stack" is)
* Once we've done this, we know how high the "top of Stack is" because
it is the height of the "pure Python" Stack we get by unwinding the
first (top-most) Frame of the on-CPU Task. We need to remember that
"height" to push that many items from the Python Thread Stack on top of
each Task's Stack.
* One final thing to keep in mind is that we "stack" Stacks (hehe) such
that if `Task-1` is awaiting `Task-2`, the Stack for `Task-2` goes under
that for `Task-1`. We only ever want to add the "pure Python
top-of-stack" once per Stack, so we need to do that _once per leaf Task_
after we've recursively unwound awaiting Tasks for the leaf Task.

### ... and a race condition?

On top of that – because it's not enough – I think I discovered a rare
but very real race condition (which actually was the root cause of that
weird, rare but common-in-CI bug with the stack I showed on top). The
race condition happens when the pure Python Stack we capture involves
some asynchronous Frames, but the associated Task/Coroutine completes or
yields before we get to unwinding it. In that case, we assume in Stack
interleaving that the Task is running, by doing so we include some
Frames from the Python Stack that actually _are not_ in the Stack
generated by unwinding the Task, and because we share the same Python
Stack for all Tasks (we only use it's "upper part", which is the same
for every Task) some Frames from the
previously-running-but-now-paused-or-completed Coroutine are leaked to
other Tasks.

Working around this is not simple; also honestly we should have a
discussion around whether we want to properly work around it (which is
going to be somewhat difficult, imperfect and probably somewhat costly)
or just give up on sampling when we detect something is off.
In the interest of keeping things somewhat simple, this will be handled
in a separate PR. But I described the bug here anyway, for clarity
(temporary PR: KowalskiThomas/echion#43)

### Caveats

I realised after the fact that an assumption we implicitly make (that
_the on-CPU Task – if it exists – is a Leaf Task_) is actually not
generally true. In the case of certain `asyncio` utils, the Parent Task
will actually from time to time execute code/be on-CPU to manage the
Child Tasks it is awaiting on. This is an edge case, and something that
happens rarely, but saying it can never happen is false (and it shows in
Profiles).
We will also need to figure something out for that – it probably isn't
_that_ hard but will require some refactors (probably split the
unwinding in two steps: (1) only determine upper Python Stack (2) unwind
Tasks strictly speaking, starting from Leaf Tasks).


## Testing

The PR adds new tests around on-CPU Tasks and what their Stacks look
like

The PR also updates a lot of existing tests to output their
`DataSummary` as JSON. This is immensely useful to understand what is
actually going on when we don't see the expected Stacks (or see the
unexpected ones) and I do think it'd be worth keeping.

After these changes, the tests that still fail locally and in the CI
(flakily) are unrelated to on-CPU Tasks which, I guess, means _mission
failed successfully_?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@taegyunkim taegyunkim taegyunkim approved these changes

@vlad-scherbich vlad-scherbich Awaiting requested review from vlad-scherbich vlad-scherbich is a code owner automatically assigned from DataDog/profiling-python

@gnufede gnufede Awaiting requested review from gnufede gnufede is a code owner automatically assigned from DataDog/apm-python

Assignees

No one assigned

Labels

Profiling Continous Profling

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@KowalskiThomas @taegyunkim