Skip to content

Spawn the sidecar via linker instead of trampoline#3869

Merged
bwoebi merged 11 commits into
masterfrom
bob/direct-exec
May 13, 2026
Merged

Spawn the sidecar via linker instead of trampoline#3869
bwoebi merged 11 commits into
masterfrom
bob/direct-exec

Conversation

@bwoebi

@bwoebi bwoebi commented May 8, 2026

Copy link
Copy Markdown
Collaborator

Alternative to #3711 and #3713

@bwoebi
bwoebi requested review from a team as code owners May 8, 2026 17:20

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 4219f07966

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread config.m4
Comment thread components-rs/php_sidecar_mockgen/src/bin/php_sidecar_mockgen.rs Outdated
@bwoebi
bwoebi force-pushed the bob/direct-exec branch 3 times, most recently from 3a6adfc to f613be8 Compare May 8, 2026 17:48
@datadog-datadog-prod-us1

datadog-datadog-prod-us1 Bot commented May 8, 2026

Copy link
Copy Markdown

Tests

🎉 All green!

❄️ No new flaky tests detected
🧪 All tests passed

🎯 Code Coverage (details)
Patch Coverage: 100.00%
Overall Coverage: 60.67% (-0.05%)

This comment will be updated automatically if new data arrives.
🔗 Commit SHA: 2d856bd | Docs | Datadog PR Page | Give us feedback!

@bwoebi
bwoebi force-pushed the bob/direct-exec branch 18 times, most recently from 0ca8690 to 9677294 Compare May 10, 2026 01:25
bwoebi added 4 commits May 11, 2026 20:18
Signed-off-by: Bob Weinand <[email protected]>
Signed-off-by: Bob Weinand <[email protected]>
Signed-off-by: Bob Weinand <[email protected]>
Signed-off-by: Bob Weinand <[email protected]>
@bwoebi
bwoebi force-pushed the bob/direct-exec branch from cd9023b to 5932697 Compare May 11, 2026 18:20
Signed-off-by: Bob Weinand <[email protected]>
@bwoebi
bwoebi force-pushed the bob/direct-exec branch 3 times, most recently from 8a7b8f5 to 6ebbff3 Compare May 12, 2026 13:25
Signed-off-by: Bob Weinand <[email protected]>
@bwoebi
bwoebi force-pushed the bob/direct-exec branch from 6ebbff3 to a78b9fe Compare May 12, 2026 13:52
Signed-off-by: Bob Weinand <[email protected]>
@bwoebi
bwoebi force-pushed the bob/direct-exec branch from 25689e8 to c0d82de Compare May 12, 2026 16:24
Signed-off-by: Bob Weinand <[email protected]>

// Let time to write the telemetry log
usleep(10000);
usleep(300000);

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Is this normal ? Why such a bump in value is needed

@bwoebi bwoebi May 13, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

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

I think some occasional recent loader test flakiness from that. We have other tests, which also have 300ms here, and which do actually not flake.

Ultimately, this test waits on the sidecar to fully initialize and submit this telemetry. This isn't strictly related to this PR.

Signed-off-by: Bob Weinand <[email protected]>
@bwoebi
bwoebi force-pushed the bob/direct-exec branch from ba76279 to 0b346ad Compare May 13, 2026 17:01
@pr-commenter

pr-commenter Bot commented May 13, 2026

Copy link
Copy Markdown

Benchmarks [ tracer ]

Benchmark execution time: 2026-05-13 21:16:55

Comparing candidate commit 2d856bd in PR branch bob/direct-exec with baseline commit 7bb186d in branch master.

Found 2 performance improvements and 20 performance regressions! Performance is the same for 161 metrics, 11 unstable metrics.

scenario:ContextPropagationBench/benchInject64Bit-opcache

  • 🟥 execution_time [+9.653µs; +9.929µs] or [+74.075%; +76.198%]

scenario:HookBench/benchHookOverheadTraceMethod-opcache

  • 🟥 execution_time [+6.900µs; +10.389µs] or [+4.049%; +6.097%]

scenario:MessagePackSerializationBench/benchMessagePackSerialization

  • 🟩 execution_time [-5.450µs; -2.910µs] or [-5.159%; -2.754%]

scenario:MessagePackSerializationBench/benchMessagePackSerialization-opcache

  • 🟩 execution_time [-7.041µs; -5.919µs] or [-6.534%; -5.493%]

scenario:PDOBench/benchPDOOverhead

  • 🟥 execution_time [+8.837µs; +12.090µs] or [+3.556%; +4.865%]

scenario:PDOBench/benchPDOOverhead-opcache

  • 🟥 execution_time [+11.544µs; +12.955µs] or [+4.698%; +5.273%]

scenario:PDOBench/benchPDOOverheadWithDBM

  • 🟥 execution_time [+8.987µs; +11.582µs] or [+3.625%; +4.671%]

scenario:PDOBench/benchPDOOverheadWithDBM-opcache

  • 🟥 execution_time [+9.838µs; +12.240µs] or [+3.978%; +4.950%]

scenario:PHPRedisBench/benchRedisOverhead

  • 🟥 execution_time [+42.137µs; +54.956µs] or [+4.357%; +5.682%]

scenario:PHPRedisBench/benchRedisOverhead-opcache

  • 🟥 execution_time [+43.035µs; +55.577µs] or [+4.259%; +5.500%]

scenario:SamplingRuleMatchingBench/benchGlobMatching1

  • 🟥 execution_time [+10.092µs; +10.321µs] or [+401.923%; +411.012%]

scenario:SamplingRuleMatchingBench/benchGlobMatching2

  • 🟥 execution_time [+9.941µs; +10.138µs] or [+377.196%; +384.677%]

scenario:SamplingRuleMatchingBench/benchGlobMatching2-opcache

  • 🟥 execution_time [+10.283µs; +10.491µs] or [+376.596%; +384.231%]

scenario:SamplingRuleMatchingBench/benchGlobMatching3

  • 🟥 execution_time [+9.992µs; +10.253µs] or [+373.169%; +382.911%]

scenario:SamplingRuleMatchingBench/benchGlobMatching3-opcache

  • 🟥 execution_time [+10.331µs; +10.568µs] or [+362.379%; +370.713%]

scenario:SamplingRuleMatchingBench/benchGlobMatching4

  • 🟥 execution_time [+10.162µs; +10.374µs] or [+383.795%; +391.799%]

scenario:SpanBench/benchDatadogAPI

  • 🟥 execution_time [+13.413µs; +14.741µs] or [+20.550%; +22.585%]

scenario:SpanBench/benchDatadogAPI-opcache

  • 🟥 execution_time [+12.848µs; +14.340µs] or [+19.602%; +21.879%]

scenario:SpanBench/benchOpenTelemetryAPI

  • 🟥 execution_time [+33.536µs; +44.155µs] or [+4.643%; +6.113%]

scenario:SpanBench/benchOpenTelemetryAPI-opcache

  • 🟥 execution_time [+33.946µs; +42.250µs] or [+5.035%; +6.266%]

scenario:SpanBench/benchOpenTelemetryInteroperability

  • 🟥 execution_time [+106.962µs; +110.184µs] or [+56.760%; +58.470%]

scenario:SpanBench/benchOpenTelemetryInteroperability-opcache

  • 🟥 execution_time [+111.747µs; +115.129µs] or [+63.780%; +65.710%]

@bwoebi
bwoebi merged commit 9c22110 into master May 13, 2026
2115 of 2122 checks passed
@bwoebi
bwoebi deleted the bob/direct-exec branch May 13, 2026 23:35
@github-actions github-actions Bot added this to the 1.20.0 milestone May 13, 2026
bwoebi added a commit that referenced this pull request May 14, 2026
* Add direct exec capabilities of the sidecar via dynamic linker

Signed-off-by: Bob Weinand <[email protected]>

* Fix race condition

Signed-off-by: Bob Weinand <[email protected]>

* Fix race condition

Signed-off-by: Bob Weinand <[email protected]>

* DEBUG

Signed-off-by: Bob Weinand <[email protected]>

* Weaken on mac and linux

Signed-off-by: Bob Weinand <[email protected]>

* Remove mockgen

Signed-off-by: Bob Weinand <[email protected]>

* Dummy

Signed-off-by: Bob Weinand <[email protected]>

* Dummy

Signed-off-by: Bob Weinand <[email protected]>

* Fix test

Signed-off-by: Bob Weinand <[email protected]>

* Cleanup

Signed-off-by: Bob Weinand <[email protected]>

* Disable direct exec for benchmarks

---------

Signed-off-by: Bob Weinand <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants