add Netty epoll/NIO-select TaskBlock instrumentation

[kaahos]

What Does This Do

Adds TaskBlock instrumentation for NIO Selector.select and Netty epoll event-loop blocking, following the same pattern established for LockSupport (#11545) and Thread.sleep (#11546). Includes:

• nio-select and netty-epoll-4.1 instrumentation modules
• Forked instrumentation tests and disabled/enabled coverage tests
• End-to-end smoke tests (NioSelectTaskBlockProfilingTest, NettyEpollTaskBlockProfilingTest) asserting on resulting TaskBlock recordings
• Native I/O TaskBlock smoke coverage (NativeIoTaskBlockProfilingTest)

This is stacked on #11546 (Thread.sleep), #11545 (LockSupport), and #11544 (foundational TaskBlock support), and should be reviewed/merged in that order.

Motivation

Selector-based I/O waits and Netty's epoll event loop are common sources of off-CPU time that for now show up only as generic sampled wall-clock frames. Emitting structured datadog.TaskBlock events for these operations, as already done for locks and sleeps, gives users accurate attribution of NIO and Netty event-loop blocking without relying solely on stack sampling.

Additional Notes

• CI (.gitlab-ci.yml) updated to build/track the corresponding java-profiler TaskBlock branch changes needed for this coverage.
• Depends on the same java-profiler PR #666 as Add wallclock TaskBlock profiler support #11544.

Contributor Checklist

• Format the title according to the contribution guidelines
• Assign the type: and (comp: or inst:) labels in addition to any other useful labels
• Avoid using close, fix, or any linking keywords when referencing an issue
  Use solves instead, and assign the PR milestone to the issue
• Update the CODEOWNERS file on source file addition, migration, or deletion
• Update public documentation with any new configuration flags or behaviors
• Once approved, use merge queue to merge the PR

Jira ticket: [PROJ-IDENT]

[dd-octo-sts]

🟢 Java Benchmark SLOs — All performance SLOs passed

Suite	Status
Startup	🟢 pass

SLO thresholds are defined here based on automatically generated metrics. A warning is raised when results are within 5% of the threshold.

PR vs. master results

Scenario	Candidate	master	Δ (95% CI of mean)
startup:insecure-bank:iast:Agent	13.98 s	13.90 s	[-0.2%; +1.3%] (no difference)
startup:insecure-bank:tracing:Agent	12.99 s	12.92 s	[-0.3%; +1.3%] (no difference)
startup:petclinic:appsec:Agent	16.87 s	16.79 s	[-0.4%; +1.3%] (no difference)
startup:petclinic:iast:Agent	16.95 s	17.05 s	[-1.4%; +0.2%] (no difference)
startup:petclinic:profiling:Agent	16.62 s	16.73 s	[-1.9%; +0.6%] (no difference)
startup:petclinic:sca:Agent	16.89 s	16.63 s	[+0.5%; +2.6%] (maybe worse)
startup:petclinic:tracing:Agent	16.16 s	16.34 s	[-1.9%; -0.2%] (maybe better)

Commit: e5e33d7f · CI Pipeline · Benchmarking Platform UI

---

Load and DaCapo benchmarks can be triggered manually in the GitLab pipeline. Results will appear in the Benchmarking Platform UI after completion.