Drop per-call String allocation in SharedDBCommenter.containsTraceComment by dougqh · Pull Request #11734 · DataDog/dd-trace-java

dougqh · 2026-06-24T20:47:44Z

What This Does

Reduces allocation SQL comment injection, but removing unnecessary allocation during contains checks

Motivation

Reduce allocation overhead

Additional Notes

SharedDBCommenter.containsTraceComment built nine KEY + "=" needle strings on every call. The keys are static final but initialized via encode(...), so they are not compile-time constants — each KEY + "=" is a runtime concatenation. A non-matching comment ran all nine checks and allocated nine throwaway Strings per call.

This hoists the needles to *_EQ constants computed once at class init. The contains-chain is otherwise unchanged.

Measured

SharedDBCommenterBenchmark (added here) — JDK 25, @Threads(8), @Fork(5), -prof gc:

	throughput	`gc.alloc.rate.norm`
before (concat)	29.7M ± 1.7M ops/s	156 B/op
after (`*_EQ`)	55.4M ± 2.5M ops/s	≈ 0

~1.9× throughput, allocation eliminated. Per our usual approach the allocation win is surfaced as a throughput delta at @Threads(8) (GC is a shared-heap tax); -prof gc corroborates the mechanism (156 → 0 B/op). Numbers live in the benchmark's class Javadoc.

🤖 Generated with Claude Code

SharedDBCommenter.containsTraceComment built nine "KEY + =" strings on every call: the keys are encode()-derived (not compile-time constants), so each "KEY + =" is a runtime concat. A non-matching comment ran all nine checks and allocated nine throwaway Strings per call. Precompute the needles once at class init as *_EQ constants; the contains-chain is unchanged. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

@threads

Throughput benchmark at @threads(8) over a realistic comment-content mix (mostly non-DD, the all-nine-checks worst case) to surface the per-call allocation removed by hoisting the "<key>=" needles to constants. Run the parent commit (baseline) vs this branch and read the ops/s delta; -prof gc (gc.alloc.rate.norm) corroborates the mechanism. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

dd-octo-sts · 2026-06-24T21:09:12Z

🟢 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	13.95 s	14.00 s	[-1.1%; +0.5%] (no difference)
startup:insecure-bank:tracing:Agent	12.94 s	13.02 s	[-1.5%; +0.2%] (no difference)
startup:petclinic:appsec:Agent	16.90 s	16.74 s	[-0.0%; +2.0%] (no difference)
startup:petclinic:iast:Agent	16.94 s	16.39 s	[-1.1%; +7.8%] (no difference)
startup:petclinic:profiling:Agent	16.90 s	16.99 s	[-1.5%; +0.5%] (no difference)
startup:petclinic:sca:Agent	16.94 s	16.80 s	[-0.2%; +1.8%] (no difference)
startup:petclinic:tracing:Agent	16.19 s	16.12 s	[-0.9%; +1.7%] (no difference)

Commit: 69f380b3 · 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.

zulu-17 @fork(5), -prof gc: 33.5M -> 62.1M ops/s (~1.9x), 156 -> ~0 B/op. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

dougqh · 2026-06-25T11:35:26Z

Benchmark results (zulu-17, JDK 17.0.7, `@Threads(8)`, `@Fork(5)`, `-prof gc`)

SharedDBCommenterBenchmark.containsTraceComment — the per-query check run during inject:

	throughput	gc.alloc.rate.norm
before (concat)	33.5M ± 2.0M ops/s	156 B/op
after (`*_EQ`)	62.1M ± 3.8M ops/s	~0 B/op (10⁻⁵)

Removing the per-call KEY + "=" concatenation drops allocation to ~0 and lifts throughput ~1.9× at @Threads(8) — the allocation win surfacing as throughput, exactly as intended. Benchmark Javadoc refreshed in 9426141.

dd-octo-sts · 2026-06-25T18:17:27Z

/merge

gh-worker-devflow-routing-ef8351 · 2026-06-25T18:17:31Z

View all feedbacks in Devflow UI.

2026-06-25 18:17:31 UTC ℹ️ Start processing command /merge

2026-06-25 18:17:35 UTC ℹ️ MergeQueue: pull request added to the queue

The expected merge time in master is approximately 1h (p90).

2026-06-25 20:17:56 UTC ❌ MergeQueue: The build pipeline has timeout

The merge request has been interrupted because the build 1513741081229096535 took longer than expected. The current limit for the base branch 'master' is 120 minutes.

dd-octo-sts · 2026-06-26T02:48:02Z

/merge

gh-worker-devflow-routing-ef8351 · 2026-06-26T02:48:06Z

View all feedbacks in Devflow UI.

2026-06-26 02:48:06 UTC ℹ️ Start processing command /merge

2026-06-26 02:48:11 UTC ℹ️ MergeQueue: pull request added to the queue

The expected merge time in master is approximately 1h (p90).

2026-06-26 04:48:34 UTC 🚨 MergeQueue: This merge request is in error

error while getting head build completion result

Details

Error: There was an error while retrieving the result for pipeline 121199058

FullStacktrace:
child workflow execution error (type: mergequeue_private.MergeQueue_WaitForChecksOrUntilIsFinal, workflowID: 019f01d3-e019-71ad-adca-ac953e874519_72, runID: 019f01d4-438a-70fd-8c67-14b35b576488, initiatedEventID: 72, startedEventID: 73): child workflow execution error (type: mergequeue.MergeQueue_WaitForCompletionOfRef, workflowID: 019f01d4-438a-70fd-8c67-14b35b576488_8, runID: 019f01d4-4469-74d4-9748-02a48752b10e, initiatedEventID: 8, startedEventID: 10): There was an error while retrieving the result for pipeline 121199058 (type: FlowError, retryable: false): There was an error while retrieving the result for pipeline 121199058

dd-octo-sts · 2026-06-29T15:59:37Z

/merge

gh-worker-devflow-routing-ef8351 · 2026-06-29T15:59:40Z

View all feedbacks in Devflow UI.

2026-06-29 15:59:40 UTC ℹ️ Start processing command /merge

2026-06-29 15:59:45 UTC ℹ️ MergeQueue: pull request added to the queue

The expected merge time in master is approximately 1h (p90).

2026-06-29 17:03:07 UTC ℹ️ MergeQueue: This merge request was merged

@threads

…ment (#11734) Hoist containsTraceComment "<key>=" needles to constants SharedDBCommenter.containsTraceComment built nine "KEY + =" strings on every call: the keys are encode()-derived (not compile-time constants), so each "KEY + =" is a runtime concat. A non-matching comment ran all nine checks and allocated nine throwaway Strings per call. Precompute the needles once at class init as *_EQ constants; the contains-chain is unchanged. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Add SharedDBCommenterBenchmark for containsTraceComment Throughput benchmark at @threads(8) over a realistic comment-content mix (mostly non-DD, the all-nine-checks worst case) to surface the per-call allocation removed by hoisting the "<key>=" needles to constants. Run the parent commit (baseline) vs this branch and read the ops/s delta; -prof gc (gc.alloc.rate.norm) corroborates the mechanism. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Refresh SharedDBCommenterBenchmark results to JDK 17 @fork(5) zulu-17 @fork(5), -prof gc: 33.5M -> 62.1M ops/s (~1.9x), 156 -> ~0 B/op. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Merge branch 'master' into dougqh/dbcommenter-alloc Merge branch 'master' into dougqh/dbcommenter-alloc Co-authored-by: devflow.devflow-routing-intake <devflow.devflow-routing-intake@kubernetes.us1.ddbuild.io>

dougqh and others added 2 commits June 24, 2026 15:56

dougqh added tag: performance Performance related changes tag: no release notes Changes to exclude from release notes type: refactoring comp: database Database Monitoring tag: ai generated Largely based on code generated by an AI or LLM labels Jun 24, 2026

dougqh marked this pull request as ready for review June 24, 2026 20:51

dougqh requested review from a team as code owners June 24, 2026 20:51

dougqh requested review from mhlidd and vandonr and removed request for a team June 24, 2026 20:51

dougqh mentioned this pull request Jun 24, 2026

Reduce per-query allocations in SQLCommenter.inject() #11154

Closed

3 tasks

dougqh mentioned this pull request Jun 24, 2026

Check the DBM comment region in place, dropping the duplicate-comment substring #11737

Open

na-ji approved these changes Jun 25, 2026

View reviewed changes

Refresh SharedDBCommenterBenchmark results to JDK 17 @fork(5)

9426141

zulu-17 @fork(5), -prof gc: 33.5M -> 62.1M ops/s (~1.9x), 156 -> ~0 B/op. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

dougqh added this pull request to the merge queue Jun 25, 2026

github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Jun 25, 2026

dougqh added this pull request to the merge queue Jun 26, 2026

github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Jun 26, 2026

dougqh added 2 commits June 29, 2026 08:39

Merge branch 'master' into dougqh/dbcommenter-alloc

0197bd0

Merge branch 'master' into dougqh/dbcommenter-alloc

69f380b

dougqh enabled auto-merge June 29, 2026 15:46

dougqh added this pull request to the merge queue Jun 29, 2026

github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Jun 29, 2026

gh-worker-dd-mergequeue-cf854d Bot merged commit 59b2142 into master Jun 29, 2026
583 checks passed

gh-worker-dd-mergequeue-cf854d Bot deleted the dougqh/dbcommenter-alloc branch June 29, 2026 17:03

github-actions Bot added this to the 1.64.0 milestone Jun 29, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Drop per-call String allocation in SharedDBCommenter.containsTraceComment#11734

Drop per-call String allocation in SharedDBCommenter.containsTraceComment#11734
gh-worker-dd-mergequeue-cf854d[bot] merged 5 commits into
masterfrom
dougqh/dbcommenter-alloc

dougqh commented Jun 24, 2026 •

edited

Loading

Uh oh!

dd-octo-sts Bot commented Jun 24, 2026 •

edited

Loading

Uh oh!

dougqh commented Jun 25, 2026

Uh oh!

dd-octo-sts Bot commented Jun 25, 2026

Uh oh!

gh-worker-devflow-routing-ef8351 Bot commented Jun 25, 2026 •

edited

Loading

Uh oh!

Uh oh!

dd-octo-sts Bot commented Jun 26, 2026

Uh oh!

gh-worker-devflow-routing-ef8351 Bot commented Jun 26, 2026 •

edited

Loading

Uh oh!

Uh oh!

dd-octo-sts Bot commented Jun 29, 2026

Uh oh!

gh-worker-devflow-routing-ef8351 Bot commented Jun 29, 2026 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

dougqh commented Jun 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What This Does

Motivation

Additional Notes

Measured

Uh oh!

dd-octo-sts Bot commented Jun 24, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🟢 Java Benchmark SLOs — All performance SLOs passed

Uh oh!

dougqh commented Jun 25, 2026

Benchmark results (zulu-17, JDK 17.0.7, @Threads(8), @Fork(5), -prof gc)

Uh oh!

dd-octo-sts Bot commented Jun 25, 2026

Uh oh!

gh-worker-devflow-routing-ef8351 Bot commented Jun 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

dd-octo-sts Bot commented Jun 26, 2026

Uh oh!

gh-worker-devflow-routing-ef8351 Bot commented Jun 26, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

dd-octo-sts Bot commented Jun 29, 2026

Uh oh!

gh-worker-devflow-routing-ef8351 Bot commented Jun 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

dougqh commented Jun 24, 2026 •

edited

Loading

dd-octo-sts Bot commented Jun 24, 2026 •

edited

Loading

Benchmark results (zulu-17, JDK 17.0.7, `@Threads(8)`, `@Fork(5)`, `-prof gc`)

gh-worker-devflow-routing-ef8351 Bot commented Jun 25, 2026 •

edited

Loading

gh-worker-devflow-routing-ef8351 Bot commented Jun 26, 2026 •

edited

Loading

gh-worker-devflow-routing-ef8351 Bot commented Jun 29, 2026 •

edited

Loading