Skip to content

perf(profiling): avoid FFI call on allocation hot path - #4068

Merged
realFlowControl merged 1 commit into
masterfrom
florian/allocation-profiler-fast-execute-data
Jul 28, 2026
Merged

perf(profiling): avoid FFI call on allocation hot path#4068
realFlowControl merged 1 commit into
masterfrom
florian/allocation-profiler-fast-execute-data

Conversation

@realFlowControl

@realFlowControl realFlowControl commented Jul 27, 2026

Copy link
Copy Markdown
Member

Description

Read executor_globals.current_execute_data directly on NTS builds instead of calling through the C FFI wrapper for every allocation and reallocation. Keep the existing wrapper on ZTS builds.

A 60-second macOS sample reduced get_current_execute_data self time from 0.412% (207/50,210 main-thread samples) to 0.002% (1/49,737). Known allocation-hook self time fell from 4.184% to 3.601%, a 13.9% relative reduction. Repeated end-to-end throughput remained within system scheduling noise.

Reviewer checklist

  • Test coverage seems ok.
  • Appropriate labels assigned.

https://datadoghq.atlassian.net/browse/PROF-15505

@realFlowControl
perf(profiling): avoid FFI call on allocation hot path
241f72a 
Read executor_globals.current_execute_data directly on NTS builds instead of calling through the C FFI wrapper for every allocation and reallocation. Keep the existing wrapper on ZTS builds.

A 60-second macOS sample reduced get_current_execute_data self time from 0.412% (207/50,210 main-thread samples) to 0.002% (1/49,737). Known allocation-hook self time fell from 4.184% to 3.601%, a 13.9% relative reduction. Repeated end-to-end throughput remained within system scheduling noise.

Validation: cargo test (22 passed); allocation sampling-distance, memory-peak, and GC PHPTs passed.
@realFlowControl
realFlowControl requested a review from a team as a code owner July 27, 2026 14:44
@github-actions github-actions Bot added profiling Relates to the Continuous Profiler tracing labels Jul 27, 2026
@realFlowControl
realFlowControl marked this pull request as draft July 27, 2026 14:49
@datadog-official

datadog-official Bot commented Jul 27, 2026 •
edited
Loading

Copy link
Copy Markdown

Pipelines  Tests

⚠️ Warnings

🚦 2 Pipeline jobs failed

DataDog/apm-reliability/dd-trace-php | appsec integration tests: [test8.4-release]   View in Datadog   GitLab

🧪 1 Test failed

All test failures are known flaky.

❄️ Known flaky: extended heartbeat re-emits configuration, dependencies and integrations() from com.datadog.appsec.php.integration.TelemetryExtendedHeartbeatTests   View in Datadog 
java.lang.AssertionError: phpredis not emitted via app-started/app-integrations-change; saw: []. Expression: (phpredis in flushed). Values: flushed = []

java.lang.AssertionError: phpredis not emitted via app-started/app-integrations-change; saw: []. Expression: (phpredis in flushed). Values: flushed = []
	at org.codehaus.groovy.runtime.InvokerHelper.createAssertError(InvokerHelper.java:416)
	at com.datadog.appsec.php.integration.TelemetryExtendedHeartbeatTests.extended heartbeat re-emits configuration, dependencies and integrations(TelemetryExtendedHeartbeatTests.groovy:70)
	at java.base/java.lang.reflect.Method.invoke(Method.java:569)
	at java.base/java.util.ArrayList.forEach(ArrayList.java:1511)
	at java.base/java.util.ArrayList.forEach(ArrayList.java:1511)

Not introduced in this PR.

DataDog/apm-reliability/dd-trace-php | publish docker image for system tests   View in Datadog   GitLab

ℹ️ Info

No other issues found (see more)

❄️ No new flaky tests detected

🎯 Code Coverage (details)
• Patch Coverage: 100.00%
• Overall Coverage: 59.64% (-1.02%)

Useful? React with 👍 / 👎

This comment will be updated automatically if new data arrives.
🔗 Commit SHA: 241f72a | Docs | Datadog PR Page | Give us feedback!

@realFlowControl realFlowControl mentioned this pull request Jul 27, 2026
Merged
2 tasks
@pr-commenter

pr-commenter Bot commented Jul 27, 2026

Copy link
Copy Markdown

Benchmarks [ profiler ]

Benchmark execution time: 2026-07-27 15:06:26

Comparing candidate commit 241f72a in PR branch florian/allocation-profiler-fast-execute-data with baseline commit 0aa19a2 in branch master.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 28 metrics, 8 unstable metrics.

Explanation

This is an A/B test comparing a candidate commit's performance against that of a baseline commit. Performance changes are noted in the tables below as:

  • 🟩 = significantly better candidate vs. baseline
  • 🟥 = significantly worse candidate vs. baseline

We compute a confidence interval (CI) over the relative difference of means between metrics from the candidate and baseline commits, considering the baseline as the reference.

If the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD), the change is considered significant.

Feel free to reach out to #apm-benchmarking-platform on Slack if you have any questions.

More details about the CI and significant changes

You can imagine this CI as a range of values that is likely to contain the true difference of means between the candidate and baseline commits.

CIs of the difference of means are often centered around 0%, because often changes are not that big:

---------------------------------(------|---^--------)-------------------------------->
                              -0.6%    0%  0.3%     +1.2%
                                 |          |        |
         lower bound of the CI --'          |        |
sample mean (center of the CI) -------------'        |
         upper bound of the CI ----------------------'

As described above, a change is considered significant if the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD).

For instance, for an execution time metric, this confidence interval indicates a significantly worse performance:

----------------------------------------|---------|---(---------^---------)---------->
                                       0%        1%  1.3%      2.2%      3.1%
                                                  |   |         |         |
       significant impact threshold --------------'   |         |         |
                      lower bound of CI --------------'         |         |
       sample mean (center of the CI) --------------------------'         |
                      upper bound of CI ----------------------------------'

@realFlowControl
realFlowControl marked this pull request as ready for review July 27, 2026 16:06
bwoebi
bwoebi approved these changes Jul 27, 2026
View reviewed changes

@bwoebi bwoebi left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Looks good. Now we need to also inline the ZTS path :-)

@realFlowControl realFlowControl added Overhead Relates to latency, CPU, or memory overhead AI Generated Largely based on code generated by an AI or LLM. This label is the same across all dd-trace-* repos labels Jul 28, 2026
@realFlowControl
realFlowControl merged commit 659848d into master Jul 28, 2026
867 of 869 checks passed
@realFlowControl
realFlowControl deleted the florian/allocation-profiler-fast-execute-data branch July 28, 2026 08:06
@github-actions github-actions Bot added this to the 1.24.0 milestone Jul 28, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@bwoebi bwoebi bwoebi approved these changes

Assignees

No one assigned

Labels

AI Generated Largely based on code generated by an AI or LLM. This label is the same across all dd-trace-* repos Overhead Relates to latency, CPU, or memory overhead profiling Relates to the Continuous Profiler tracing

Projects

None yet

Milestone

1.24.0

Development

Successfully merging this pull request may close these issues.

2 participants

@realFlowControl @bwoebi