fix(trace-exporter): mark OTLP client-computed stats by bengl · Pull Request #2245 · DataDog/libdatadog

bengl · 2026-07-16T15:32:14Z

What does this PR do?

Marks OTLP trace exports as client-computed when tracer metadata already says stats were computed client-side.

This sets both:

the OTLP Resource attribute _dd.stats_computed=true
the direct Agent request header datadog-client-computed-stats: yes

when either metadata.client_computed_stats or libdatadog's native OTLP stats worker is enabled.

Motivation

dd-trace-js computes OTLP span metrics in JS and passes that state through set_client_computed_stats(). The OTLP trace exporter only looked at otlp_stats_enabled, so Resources sent by JS-backed stats did not carry _dd.stats_computed=true and system-tests rejected the payload.

Additional Notes

The native OTLP stats worker path remains unchanged because otlp_stats_enabled still sets the same Resource attribute and header.

How to test the change?

cargo test -p libdd-data-pipeline --test test_trace_exporter_otlp_export -- --nocapture

Result: 2 passed.

github-actions · 2026-07-16T15:34:42Z

📚 Documentation Check Results

⚠️ 1206 documentation warning(s) found

📦 `libdd-data-pipeline` - 1206 warning(s)

Updated: 2026-07-16 16:39:18 UTC | Commit: 76e5a6c | missing-docs job results

github-actions · 2026-07-16T15:36:30Z

🔒 Cargo Deny Results

⚠️ 3 issue(s) found, showing only errors (advisories, bans, sources)

📦 `libdd-data-pipeline` - 3 error(s)

Show output

error[vulnerability]: Invalid pointer dereference in `fmt::Pointer` impl for `Atomic` and `Shared` when the underlying pointer is invalid
   ┌─ /home/runner/work/libdatadog/libdatadog/Cargo.lock:75:1
   │
75 │ crossbeam-epoch 0.9.18 registry+https://github.com/rust-lang/crates.io-index
   │ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ security vulnerability detected
   │
   ├ ID: RUSTSEC-2026-0204
   ├ Advisory: https://rustsec.org/advisories/RUSTSEC-2026-0204
   ├ Affected versions of `fmt::Display` dereference the underlying pointer. This causes a invalid pointer dereference e.g., when a pointer created with `Atomic::null` or `Shared::null`. `fmt::Debug` impls and pre-0.9 `fmt::Display` impls, which do not dereference pointers, are not affected by this issue.
   ├ Announcement: https://github.com/crossbeam-rs/crossbeam/pull/1276
   ├ Solution: Upgrade to >=0.9.20 (try `cargo update -p crossbeam-epoch`)
   ├ crossbeam-epoch v0.9.18
     └── crossbeam-deque v0.8.5
         └── rayon-core v1.12.1
             └── rayon v1.10.0
                 └── criterion v0.5.1
                     ├── libdd-common v5.1.0
                     │   ├── libdd-capabilities-impl v3.0.0
                     │   │   ├── libdd-data-pipeline v7.0.0
                     │   │   ├── libdd-shared-runtime v2.0.0
                     │   │   │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   │   │   ├── libdd-telemetry v6.0.0
                     │   │   │   │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   │   │   │   └── libdd-trace-stats v6.0.0
                     │   │   │   │       └── libdd-data-pipeline v7.0.0 (*)
                     │   │   │   └── libdd-trace-stats v6.0.0 (*)
                     │   │   ├── libdd-trace-stats v6.0.0 (*)
                     │   │   └── libdd-trace-utils v9.0.0
                     │   │       ├── libdd-data-pipeline v7.0.0 (*)
                     │   │       ├── libdd-trace-obfuscation v5.0.0
                     │   │       │   └── libdd-trace-stats v6.0.0 (*)
                     │   │       ├── libdd-trace-stats v6.0.0 (*)
                     │   │       └── (dev) libdd-trace-utils v9.0.0 (*)
                     │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   ├── libdd-dogstatsd-client v4.0.0
                     │   │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   │   └── libdd-trace-stats v6.0.0 (*)
                     │   ├── libdd-shared-runtime v2.0.0 (*)
                     │   ├── libdd-telemetry v6.0.0 (*)
                     │   ├── libdd-trace-obfuscation v5.0.0 (*)
                     │   ├── libdd-trace-stats v6.0.0 (*)
                     │   └── libdd-trace-utils v9.0.0 (*)
                     ├── (dev) libdd-data-pipeline v7.0.0 (*)
                     ├── (dev) libdd-ddsketch v1.1.0
                     │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   ├── libdd-telemetry v6.0.0 (*)
                     │   └── libdd-trace-stats v6.0.0 (*)
                     ├── (dev) libdd-trace-normalization v3.0.0
                     │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   └── libdd-trace-utils v9.0.0 (*)
                     ├── (dev) libdd-trace-obfuscation v5.0.0 (*)
                     ├── (dev) libdd-trace-stats v6.0.0 (*)
                     └── (dev) libdd-trace-utils v9.0.0 (*)

error[unsound]: Rand is unsound with a custom logger using `rand::rng()`
    ┌─ /home/runner/work/libdatadog/libdatadog/Cargo.lock:218:1
    │
218 │ rand 0.8.5 registry+https://github.com/rust-lang/crates.io-index
    │ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ unsound advisory detected
    │
    ├ ID: RUSTSEC-2026-0097
    ├ Advisory: https://rustsec.org/advisories/RUSTSEC-2026-0097
    ├ It has been reported (by @lopopolo) that the `rand` library is [unsound](https://rust-lang.github.io/unsafe-code-guidelines/glossary.html#soundness-of-code--of-a-library) (i.e. that safe code using the public API can cause Undefined Behaviour) when all the following conditions are met:
      
      - The `log` and `thread_rng` features are enabled
      - A [custom logger](https://docs.rs/log/latest/log/#implementing-a-logger) is defined
      - The custom logger accesses `rand::rng()` (previously `rand::thread_rng()`) and calls any `TryRng` (previously `RngCore`) methods on `ThreadRng`
      - The `ThreadRng` (attempts to) reseed while called from the custom logger (this happens every 64 kB of generated data)
      - Trace-level logging is enabled or warn-level logging is enabled and the random source (the `getrandom` crate) is unable to provide a new seed
      
      `TryRng` (previously `RngCore`) methods for `ThreadRng` use `unsafe` code to cast `*mut BlockRng<ReseedingCore>` to `&mut BlockRng<ReseedingCore>`. When all the above conditions are met this results in an aliased mutable reference, violating the Stacked Borrows rules. Miri is able to detect this violation in sample code. Since construction of [aliased mutable references is Undefined Behaviour](https://doc.rust-lang.org/stable/nomicon/references.html), the behaviour of optimized builds is hard to predict.
    ├ Announcement: https://github.com/rust-random/rand/pull/1763
    ├ Solution: Upgrade to >=0.10.1 OR <0.10.0, >=0.9.3 OR <0.9.0, >=0.8.6 (try `cargo update -p rand`)
    ├ rand v0.8.5
      ├── libdd-common v5.1.0
      │   ├── libdd-capabilities-impl v3.0.0
      │   │   ├── libdd-data-pipeline v7.0.0
      │   │   ├── libdd-shared-runtime v2.0.0
      │   │   │   ├── libdd-data-pipeline v7.0.0 (*)
      │   │   │   ├── libdd-telemetry v6.0.0
      │   │   │   │   ├── libdd-data-pipeline v7.0.0 (*)
      │   │   │   │   └── libdd-trace-stats v6.0.0
      │   │   │   │       └── libdd-data-pipeline v7.0.0 (*)
      │   │   │   └── libdd-trace-stats v6.0.0 (*)
      │   │   ├── libdd-trace-stats v6.0.0 (*)
      │   │   └── libdd-trace-utils v9.0.0
      │   │       ├── libdd-data-pipeline v7.0.0 (*)
      │   │       ├── libdd-trace-obfuscation v5.0.0
      │   │       │   └── libdd-trace-stats v6.0.0 (*)
      │   │       ├── libdd-trace-stats v6.0.0 (*)
      │   │       └── (dev) libdd-trace-utils v9.0.0 (*)
      │   ├── libdd-data-pipeline v7.0.0 (*)
      │   ├── libdd-dogstatsd-client v4.0.0
      │   │   ├── libdd-data-pipeline v7.0.0 (*)
      │   │   └── libdd-trace-stats v6.0.0 (*)
      │   ├── libdd-shared-runtime v2.0.0 (*)
      │   ├── libdd-telemetry v6.0.0 (*)
      │   ├── libdd-trace-obfuscation v5.0.0 (*)
      │   ├── libdd-trace-stats v6.0.0 (*)
      │   └── libdd-trace-utils v9.0.0 (*)
      ├── (dev) libdd-data-pipeline v7.0.0 (*)
      ├── (dev) libdd-ddsketch v1.1.0
      │   ├── libdd-data-pipeline v7.0.0 (*)
      │   ├── libdd-telemetry v6.0.0 (*)
      │   └── libdd-trace-stats v6.0.0 (*)
      ├── (dev) libdd-trace-normalization v3.0.0
      │   ├── libdd-data-pipeline v7.0.0 (*)
      │   └── libdd-trace-utils v9.0.0 (*)
      ├── (dev) libdd-trace-stats v6.0.0 (*)
      ├── libdd-trace-utils v9.0.0 (*)
      └── proptest v1.5.0
          └── (dev) libdd-tinybytes v1.1.1
              ├── libdd-data-pipeline v7.0.0 (*)
              ├── (dev) libdd-tinybytes v1.1.1 (*)
              └── libdd-trace-utils v9.0.0 (*)

error[vulnerability]: Denial of Service via Stack Exhaustion
    ┌─ /home/runner/work/libdatadog/libdatadog/Cargo.lock:287:1
    │
287 │ time 0.3.41 registry+https://github.com/rust-lang/crates.io-index
    │ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ security vulnerability detected
    │
    ├ ID: RUSTSEC-2026-0009
    ├ Advisory: https://rustsec.org/advisories/RUSTSEC-2026-0009
    ├ ## Impact
      
      When user-provided input is provided to any type that parses with the RFC 2822 format, a denial of
      service attack via stack exhaustion is possible. The attack relies on formally deprecated and
      rarely-used features that are part of the RFC 2822 format used in a malicious manner. Ordinary,
      non-malicious input will never encounter this scenario.
      
      ## Patches
      
      A limit to the depth of recursion was added in v0.3.47. From this version, an error will be returned
      rather than exhausting the stack.
      
      ## Workarounds
      
      Limiting the length of user input is the simplest way to avoid stack exhaustion, as the amount of
      the stack consumed would be at most a factor of the length of the input.
    ├ Announcement: https://github.com/time-rs/time/blob/main/CHANGELOG.md#0347-2026-02-05
    ├ Solution: Upgrade to >=0.3.47 (try `cargo update -p time`)
    ├ time v0.3.41
      └── tracing-appender v0.2.3
          └── libdd-log v1.0.0
              └── (dev) libdd-data-pipeline v7.0.0

advisories FAILED, bans ok, sources ok

Updated: 2026-07-16 16:40:58 UTC | Commit: 76e5a6c | dependency-check job results

datadog-prod-us1-4 · 2026-07-16T15:39:09Z

Tests

🎉 All green!

🧪 All tests passed
❄️ No new flaky tests detected

🎯 Code Coverage (details)
• Patch Coverage: 100.00%
• Overall Coverage: 74.73% (+0.01%)

_{This comment will be updated automatically if new data arrives.

🔗 Commit SHA: 6356aee | Docs | Datadog PR Page | Give us feedback!}

pr-commenter · 2026-07-16T15:42:02Z

Benchmarks

Comparison

Benchmark execution time: 2026-07-16 16:49:19

Comparing candidate commit 6356aee in PR branch bengl/otlp-client-computed-stats with baseline commit 95d0c13 in branch main.

Found 2 performance improvements and 0 performance regressions! Performance is the same for 22 metrics, 0 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 ----------------------------------'

scenario:trace_buffer/4_senders/no_delay

🟩 execution_time [-171.484µs; -140.695µs] or [-6.981%; -5.728%]
🟩 throughput [+90567.102op/s; +111073.141op/s] or [+6.175%; +7.573%]

Candidate

Candidate benchmark details

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`6356aee`	1784219749	bengl/otlp-client-computed-stats

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
trace_buffer/1_senders/10us_delay	execution_time	56.352ms	56.610ms ± 0.146ms	56.595ms ± 0.108ms	56.710ms	56.874ms	56.967ms	57.065ms	0.83%	0.531	-0.234	0.26%	0.010ms	1	200
trace_buffer/1_senders/10us_delay	throughput	15771.624op/s	15898.249op/s ± 40.990op/s	15902.488op/s ± 30.502op/s	15932.228op/s	15956.818op/s	15968.258op/s	15971.088op/s	0.43%	-0.519	-0.253	0.26%	2.898op/s	1	200
trace_buffer/1_senders/1us_delay	execution_time	49.978ms	50.086ms ± 0.031ms	50.082ms ± 0.008ms	50.089ms	50.144ms	50.190ms	50.203ms	0.24%	1.236	3.636	0.06%	0.002ms	1	200
trace_buffer/1_senders/1us_delay	throughput	17927.292op/s	17969.194op/s ± 11.188op/s	17970.578op/s ± 2.808op/s	17973.654op/s	17983.987op/s	17990.537op/s	18007.765op/s	0.21%	-1.228	3.625	0.06%	0.791op/s	1	200
trace_buffer/1_senders/no_delay	execution_time	331.501µs	339.316µs ± 4.420µs	338.488µs ± 1.485µs	340.288µs	344.474µs	347.309µs	387.130µs	14.37%	6.771	67.882	1.30%	0.313µs	1	200
trace_buffer/1_senders/no_delay	throughput	2324801.994op/s	2652808.972op/s ± 31929.351op/s	2658879.914op/s ± 11716.513op/s	2668679.403op/s	2681297.046op/s	2691178.891op/s	2714923.937op/s	2.11%	-5.899	55.245	1.20%	2257.746op/s	1	200
trace_buffer/2_senders/10us_delay	execution_time	56.831ms	57.262ms ± 0.183ms	57.253ms ± 0.109ms	57.364ms	57.577ms	57.696ms	57.756ms	0.88%	0.308	-0.100	0.32%	0.013ms	1	200
trace_buffer/2_senders/10us_delay	throughput	31165.522op/s	31434.530op/s ± 100.407op/s	31439.492op/s ± 59.667op/s	31498.480op/s	31586.536op/s	31645.497op/s	31672.809op/s	0.74%	-0.291	-0.113	0.32%	7.100op/s	1	200
trace_buffer/2_senders/1us_delay	execution_time	50.060ms	50.121ms ± 0.031ms	50.117ms ± 0.016ms	50.133ms	50.179ms	50.212ms	50.233ms	0.23%	0.931	1.066	0.06%	0.002ms	1	200
trace_buffer/2_senders/1us_delay	throughput	35833.240op/s	35913.368op/s ± 22.168op/s	35916.190op/s ± 11.687op/s	35928.257op/s	35943.607op/s	35950.081op/s	35956.651op/s	0.11%	-0.926	1.055	0.06%	1.567op/s	1	200
trace_buffer/2_senders/no_delay	execution_time	826.807µs	877.902µs ± 20.356µs	877.613µs ± 13.503µs	892.935µs	909.349µs	928.901µs	940.995µs	7.22%	0.019	0.195	2.31%	1.439µs	1	200
trace_buffer/2_senders/no_delay	throughput	1912869.788op/s	2051441.294op/s ± 47629.351op/s	2051017.748op/s ± 31548.887op/s	2080766.298op/s	2134998.400op/s	2171114.552op/s	2177048.952op/s	6.14%	0.132	0.178	2.32%	3367.904op/s	1	200
trace_buffer/4_senders/10us_delay	execution_time	57.222ms	57.523ms ± 0.132ms	57.513ms ± 0.083ms	57.597ms	57.769ms	57.895ms	57.946ms	0.75%	0.593	0.664	0.23%	0.009ms	1	200
trace_buffer/4_senders/10us_delay	throughput	62127.181op/s	62583.926op/s ± 143.501op/s	62594.726op/s ± 90.822op/s	62684.452op/s	62776.771op/s	62891.469op/s	62912.903op/s	0.51%	-0.577	0.637	0.23%	10.147op/s	1	200
trace_buffer/4_senders/1us_delay	execution_time	50.058ms	50.176ms ± 0.042ms	50.164ms ± 0.019ms	50.201ms	50.261ms	50.294ms	50.328ms	0.33%	0.968	0.934	0.08%	0.003ms	1	200
trace_buffer/4_senders/1us_delay	throughput	71530.615op/s	71747.103op/s ± 59.434op/s	71764.500op/s ± 27.892op/s	71783.997op/s	71818.041op/s	71830.505op/s	71916.733op/s	0.21%	-0.963	0.925	0.08%	4.203op/s	1	200
trace_buffer/4_senders/no_delay	execution_time	1.985ms	2.300ms ± 0.090ms	2.300ms ± 0.060ms	2.366ms	2.430ms	2.468ms	2.502ms	8.77%	-0.483	0.503	3.88%	0.006ms	1	200
trace_buffer/4_senders/no_delay	throughput	1438744.192op/s	1567454.289op/s ± 62556.966op/s	1564896.647op/s ± 40289.483op/s	1603305.196op/s	1678114.545op/s	1749006.742op/s	1813569.010op/s	15.89%	0.768	1.166	3.98%	4423.446op/s	1	200
trace_buffer/8_senders/10us_delay	execution_time	57.675ms	58.050ms ± 0.279ms	57.934ms ± 0.143ms	58.274ms	58.621ms	58.738ms	58.771ms	1.44%	0.814	-0.527	0.48%	0.020ms	1	200
trace_buffer/8_senders/10us_delay	throughput	122508.692op/s	124033.411op/s ± 593.471op/s	124278.450op/s ± 308.575op/s	124527.418op/s	124672.344op/s	124723.865op/s	124837.033op/s	0.45%	-0.803	-0.553	0.48%	41.965op/s	1	200
trace_buffer/8_senders/1us_delay	execution_time	50.204ms	50.309ms ± 0.065ms	50.298ms ± 0.043ms	50.348ms	50.428ms	50.487ms	50.540ms	0.48%	0.866	0.634	0.13%	0.005ms	1	200
trace_buffer/8_senders/1us_delay	throughput	142460.921op/s	143114.526op/s ± 183.887op/s	143147.420op/s ± 123.800op/s	143256.022op/s	143345.409op/s	143396.221op/s	143415.836op/s	0.19%	-0.858	0.612	0.13%	13.003op/s	1	200
trace_buffer/8_senders/no_delay	execution_time	5.933ms	6.483ms ± 0.095ms	6.493ms ± 0.059ms	6.548ms	6.611ms	6.634ms	6.665ms	2.66%	-1.383	5.026	1.46%	0.007ms	1	200
trace_buffer/8_senders/no_delay	throughput	1080226.145op/s	1110768.596op/s ± 16600.541op/s	1108906.390op/s ± 10093.223op/s	1119561.772op/s	1137525.086op/s	1158372.109op/s	1213621.417op/s	9.44%	1.629	6.694	1.49%	1173.835op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
trace_buffer/1_senders/10us_delay	execution_time	[56.590ms; 56.631ms] or [-0.036%; +0.036%]	None	None	None
trace_buffer/1_senders/10us_delay	throughput	[15892.568op/s; 15903.929op/s] or [-0.036%; +0.036%]	None	None	None
trace_buffer/1_senders/1us_delay	execution_time	[50.081ms; 50.090ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/1_senders/1us_delay	throughput	[17967.644op/s; 17970.745op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/1_senders/no_delay	execution_time	[338.703µs; 339.928µs] or [-0.181%; +0.181%]	None	None	None
trace_buffer/1_senders/no_delay	throughput	[2648383.871op/s; 2657234.073op/s] or [-0.167%; +0.167%]	None	None	None
trace_buffer/2_senders/10us_delay	execution_time	[57.237ms; 57.288ms] or [-0.044%; +0.044%]	None	None	None
trace_buffer/2_senders/10us_delay	throughput	[31420.615op/s; 31448.446op/s] or [-0.044%; +0.044%]	None	None	None
trace_buffer/2_senders/1us_delay	execution_time	[50.116ms; 50.125ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/1us_delay	throughput	[35910.296op/s; 35916.440op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/no_delay	execution_time	[875.081µs; 880.723µs] or [-0.321%; +0.321%]	None	None	None
trace_buffer/2_senders/no_delay	throughput	[2044840.324op/s; 2058042.264op/s] or [-0.322%; +0.322%]	None	None	None
trace_buffer/4_senders/10us_delay	execution_time	[57.505ms; 57.541ms] or [-0.032%; +0.032%]	None	None	None
trace_buffer/4_senders/10us_delay	throughput	[62564.038op/s; 62603.814op/s] or [-0.032%; +0.032%]	None	None	None
trace_buffer/4_senders/1us_delay	execution_time	[50.171ms; 50.182ms] or [-0.011%; +0.011%]	None	None	None
trace_buffer/4_senders/1us_delay	throughput	[71738.866op/s; 71755.340op/s] or [-0.011%; +0.011%]	None	None	None
trace_buffer/4_senders/no_delay	execution_time	[2.288ms; 2.313ms] or [-0.540%; +0.540%]	None	None	None
trace_buffer/4_senders/no_delay	throughput	[1558784.495op/s; 1576124.083op/s] or [-0.553%; +0.553%]	None	None	None
trace_buffer/8_senders/10us_delay	execution_time	[58.012ms; 58.089ms] or [-0.067%; +0.067%]	None	None	None
trace_buffer/8_senders/10us_delay	throughput	[123951.162op/s; 124115.660op/s] or [-0.066%; +0.066%]	None	None	None
trace_buffer/8_senders/1us_delay	execution_time	[50.300ms; 50.318ms] or [-0.018%; +0.018%]	None	None	None
trace_buffer/8_senders/1us_delay	throughput	[143089.041op/s; 143140.011op/s] or [-0.018%; +0.018%]	None	None	None
trace_buffer/8_senders/no_delay	execution_time	[6.470ms; 6.497ms] or [-0.203%; +0.203%]	None	None	None
trace_buffer/8_senders/no_delay	throughput	[1108467.921op/s; 1113069.271op/s] or [-0.207%; +0.207%]	None	None	None

Baseline

Baseline benchmark details

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`95d0c13`	1784218428	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
trace_buffer/1_senders/10us_delay	execution_time	56.288ms	56.541ms ± 0.126ms	56.529ms ± 0.076ms	56.606ms	56.752ms	56.911ms	56.962ms	0.77%	0.750	0.699	0.22%	0.009ms	1	200
trace_buffer/1_senders/10us_delay	throughput	15799.929op/s	15917.867op/s ± 35.505op/s	15920.946op/s ± 21.497op/s	15942.397op/s	15971.338op/s	15978.412op/s	15989.178op/s	0.43%	-0.736	0.669	0.22%	2.511op/s	1	200
trace_buffer/1_senders/1us_delay	execution_time	49.973ms	50.081ms ± 0.036ms	50.080ms ± 0.014ms	50.092ms	50.146ms	50.204ms	50.209ms	0.26%	1.007	2.795	0.07%	0.003ms	1	200
trace_buffer/1_senders/1us_delay	throughput	17925.042op/s	17970.882op/s ± 12.895op/s	17971.325op/s ± 4.991op/s	17976.841op/s	17988.634op/s	17992.834op/s	18009.589op/s	0.21%	-0.999	2.780	0.07%	0.912op/s	1	200
trace_buffer/1_senders/no_delay	execution_time	333.594µs	342.265µs ± 5.708µs	341.567µs ± 2.094µs	343.750µs	347.381µs	356.842µs	405.816µs	18.81%	7.152	75.435	1.66%	0.404µs	1	200
trace_buffer/1_senders/no_delay	throughput	2217751.757op/s	2630193.281op/s ± 39565.071op/s	2634918.176op/s ± 16053.021op/s	2650020.296op/s	2668137.689op/s	2675796.596op/s	2697893.568op/s	2.39%	-5.948	57.768	1.50%	2797.673op/s	1	200
trace_buffer/2_senders/10us_delay	execution_time	56.703ms	57.201ms ± 0.228ms	57.172ms ± 0.166ms	57.356ms	57.617ms	57.704ms	57.878ms	1.24%	0.354	-0.410	0.40%	0.016ms	1	200
trace_buffer/2_senders/10us_delay	throughput	31099.756op/s	31468.576op/s ± 124.992op/s	31484.008op/s ± 91.443op/s	31564.080op/s	31641.973op/s	31707.543op/s	31744.314op/s	0.83%	-0.336	-0.427	0.40%	8.838op/s	1	200
trace_buffer/2_senders/1us_delay	execution_time	50.059ms	50.115ms ± 0.031ms	50.111ms ± 0.017ms	50.126ms	50.179ms	50.205ms	50.247ms	0.27%	1.340	2.535	0.06%	0.002ms	1	200
trace_buffer/2_senders/1us_delay	throughput	35822.751op/s	35917.517op/s ± 22.119op/s	35920.491op/s ± 11.858op/s	35933.246op/s	35944.287op/s	35950.131op/s	35957.245op/s	0.10%	-1.335	2.515	0.06%	1.564op/s	1	200
trace_buffer/2_senders/no_delay	execution_time	848.550µs	898.413µs ± 19.950µs	898.806µs ± 10.714µs	909.465µs	923.789µs	939.765µs	1035.810µs	15.24%	1.350	10.187	2.22%	1.411µs	1	200
trace_buffer/2_senders/no_delay	throughput	1737770.627op/s	2004492.918op/s ± 43508.254op/s	2002655.954op/s ± 23684.086op/s	2026068.411op/s	2080800.888op/s	2104535.738op/s	2121266.244op/s	5.92%	-0.764	6.251	2.17%	3076.498op/s	1	200
trace_buffer/4_senders/10us_delay	execution_time	57.294ms	57.577ms ± 0.174ms	57.525ms ± 0.079ms	57.632ms	57.962ms	58.177ms	58.216ms	1.20%	1.497	2.329	0.30%	0.012ms	1	200
trace_buffer/4_senders/10us_delay	throughput	61838.335op/s	62526.031op/s ± 188.387op/s	62581.554op/s ± 85.827op/s	62636.679op/s	62734.369op/s	62827.340op/s	62834.231op/s	0.40%	-1.478	2.263	0.30%	13.321op/s	1	200
trace_buffer/4_senders/1us_delay	execution_time	50.086ms	50.172ms ± 0.039ms	50.164ms ± 0.018ms	50.187ms	50.264ms	50.281ms	50.297ms	0.26%	1.154	1.106	0.08%	0.003ms	1	200
trace_buffer/4_senders/1us_delay	throughput	71575.398op/s	71753.379op/s ± 55.562op/s	71764.572op/s ± 26.119op/s	71787.307op/s	71818.934op/s	71829.441op/s	71876.413op/s	0.16%	-1.150	1.097	0.08%	3.929op/s	1	200
trace_buffer/4_senders/no_delay	execution_time	2.257ms	2.456ms ± 0.066ms	2.460ms ± 0.044ms	2.503ms	2.556ms	2.570ms	2.682ms	9.01%	-0.183	0.211	2.67%	0.005ms	1	200
trace_buffer/4_senders/no_delay	throughput	1342383.055op/s	1466634.168op/s ± 39494.006op/s	1463318.092op/s ± 25540.965op/s	1490309.950op/s	1537885.494op/s	1558207.795op/s	1594735.752op/s	8.98%	0.355	0.232	2.69%	2792.648op/s	1	200
trace_buffer/8_senders/10us_delay	execution_time	57.619ms	57.992ms ± 0.281ms	57.879ms ± 0.149ms	58.216ms	58.538ms	58.618ms	58.857ms	1.69%	0.841	-0.409	0.48%	0.020ms	1	200
trace_buffer/8_senders/10us_delay	throughput	122330.180op/s	124157.090op/s ± 599.687op/s	124396.583op/s ± 322.139op/s	124630.671op/s	124816.466op/s	124922.265op/s	124957.736op/s	0.45%	-0.828	-0.439	0.48%	42.404op/s	1	200
trace_buffer/8_senders/1us_delay	execution_time	50.173ms	50.288ms ± 0.056ms	50.271ms ± 0.028ms	50.316ms	50.410ms	50.458ms	50.508ms	0.47%	1.349	2.238	0.11%	0.004ms	1	200
trace_buffer/8_senders/1us_delay	throughput	142551.988op/s	143175.882op/s ± 158.967op/s	143224.391op/s ± 78.690op/s	143282.959op/s	143357.281op/s	143399.197op/s	143504.144op/s	0.20%	-1.341	2.209	0.11%	11.241op/s	1	200
trace_buffer/8_senders/no_delay	execution_time	5.897ms	6.591ms ± 0.122ms	6.602ms ± 0.085ms	6.685ms	6.757ms	6.774ms	6.828ms	3.43%	-1.200	4.197	1.84%	0.009ms	1	200
trace_buffer/8_senders/no_delay	throughput	1054532.410op/s	1092716.709op/s ± 20663.279op/s	1090659.850op/s ± 14116.642op/s	1104946.310op/s	1123636.503op/s	1136455.730op/s	1220939.244op/s	11.95%	1.499	6.261	1.89%	1461.114op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
trace_buffer/1_senders/10us_delay	execution_time	[56.523ms; 56.558ms] or [-0.031%; +0.031%]	None	None	None
trace_buffer/1_senders/10us_delay	throughput	[15912.946op/s; 15922.788op/s] or [-0.031%; +0.031%]	None	None	None
trace_buffer/1_senders/1us_delay	execution_time	[50.076ms; 50.086ms] or [-0.010%; +0.010%]	None	None	None
trace_buffer/1_senders/1us_delay	throughput	[17969.095op/s; 17972.669op/s] or [-0.010%; +0.010%]	None	None	None
trace_buffer/1_senders/no_delay	execution_time	[341.474µs; 343.056µs] or [-0.231%; +0.231%]	None	None	None
trace_buffer/1_senders/no_delay	throughput	[2624709.943op/s; 2635676.619op/s] or [-0.208%; +0.208%]	None	None	None
trace_buffer/2_senders/10us_delay	execution_time	[57.169ms; 57.232ms] or [-0.055%; +0.055%]	None	None	None
trace_buffer/2_senders/10us_delay	throughput	[31451.253op/s; 31485.899op/s] or [-0.055%; +0.055%]	None	None	None
trace_buffer/2_senders/1us_delay	execution_time	[50.111ms; 50.119ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/1us_delay	throughput	[35914.452op/s; 35920.583op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/no_delay	execution_time	[895.648µs; 901.178µs] or [-0.308%; +0.308%]	None	None	None
trace_buffer/2_senders/no_delay	throughput	[1998463.093op/s; 2010522.744op/s] or [-0.301%; +0.301%]	None	None	None
trace_buffer/4_senders/10us_delay	execution_time	[57.552ms; 57.601ms] or [-0.042%; +0.042%]	None	None	None
trace_buffer/4_senders/10us_delay	throughput	[62499.923op/s; 62552.140op/s] or [-0.042%; +0.042%]	None	None	None
trace_buffer/4_senders/1us_delay	execution_time	[50.166ms; 50.177ms] or [-0.011%; +0.011%]	None	None	None
trace_buffer/4_senders/1us_delay	throughput	[71745.678op/s; 71761.079op/s] or [-0.011%; +0.011%]	None	None	None
trace_buffer/4_senders/no_delay	execution_time	[2.447ms; 2.465ms] or [-0.371%; +0.371%]	None	None	None
trace_buffer/4_senders/no_delay	throughput	[1461160.679op/s; 1472107.657op/s] or [-0.373%; +0.373%]	None	None	None
trace_buffer/8_senders/10us_delay	execution_time	[57.953ms; 58.031ms] or [-0.067%; +0.067%]	None	None	None
trace_buffer/8_senders/10us_delay	throughput	[124073.979op/s; 124240.201op/s] or [-0.067%; +0.067%]	None	None	None
trace_buffer/8_senders/1us_delay	execution_time	[50.280ms; 50.296ms] or [-0.015%; +0.015%]	None	None	None
trace_buffer/8_senders/1us_delay	throughput	[143153.850op/s; 143197.913op/s] or [-0.015%; +0.015%]	None	None	None
trace_buffer/8_senders/no_delay	execution_time	[6.575ms; 6.608ms] or [-0.256%; +0.256%]	None	None	None
trace_buffer/8_senders/no_delay	throughput	[1089852.977op/s; 1095580.441op/s] or [-0.262%; +0.262%]	None	None	None

yannham · 2026-07-16T15:52:51Z

+                        }) && attrs.iter().any(|attr| {
+                            attr.get("key").and_then(Value::as_str) == Some("_dd.stats_computed")
+                                && attr.pointer("/value/stringValue").and_then(Value::as_str)
+                                    == Some("true")


Out of curiosity, why can't the new test be implemented in term of json_body_includes? I'm not sure how it works exactly, but naively it looks like the previous payload could be extended for _dd.stats_computed

dd-octo-sts · 2026-07-16T16:35:29Z

Artifact Size Benchmark Report

aarch64-alpine-linux-musl

Artifact	Baseline	Commit	Change
/aarch64-alpine-linux-musl/lib/libdatadog_profiling.a	86.33 MB	86.33 MB	+0% (+56 B) 👌
/aarch64-alpine-linux-musl/lib/libdatadog_profiling.so	7.88 MB	7.88 MB	0% (0 B) 👌

aarch64-unknown-linux-gnu

Artifact	Baseline	Commit	Change
/aarch64-unknown-linux-gnu/lib/libdatadog_profiling.a	97.54 MB	97.54 MB	+0% (+136 B) 👌
/aarch64-unknown-linux-gnu/lib/libdatadog_profiling.so	10.62 MB	10.62 MB	0% (0 B) 👌

libdatadog-x64-windows

Artifact	Baseline	Commit	Change
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.dll	25.58 MB	25.58 MB	0% (0 B) 👌
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.lib	89.18 KB	89.18 KB	0% (0 B) 👌
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.pdb	185.48 MB	185.46 MB	--.01% (-24.00 KB) 💪
/libdatadog-x64-windows/debug/static/datadog_profiling_ffi.lib	958.37 MB	958.37 MB	+0% (+128 B) 👌
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.dll	8.37 MB	8.37 MB	0% (0 B) 👌
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.lib	89.18 KB	89.18 KB	0% (0 B) 👌
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.pdb	24.76 MB	24.76 MB	0% (0 B) 👌
/libdatadog-x64-windows/release/static/datadog_profiling_ffi.lib	49.28 MB	49.28 MB	+0% (+90 B) 👌

libdatadog-x86-windows

Artifact	Baseline	Commit	Change
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.dll	22.23 MB	22.23 MB	0% (0 B) 👌
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.lib	90.58 KB	90.58 KB	0% (0 B) 👌
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.pdb	189.97 MB	189.95 MB	-0% (-16.00 KB) 👌
/libdatadog-x86-windows/debug/static/datadog_profiling_ffi.lib	946.26 MB	946.26 MB	+0% (+96 B) 👌
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.dll	6.47 MB	6.47 MB	0% (0 B) 👌
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.lib	90.58 KB	90.58 KB	0% (0 B) 👌
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.pdb	26.59 MB	26.59 MB	0% (0 B) 👌
/libdatadog-x86-windows/release/static/datadog_profiling_ffi.lib	46.90 MB	46.90 MB	+0% (+60 B) 👌

x86_64-alpine-linux-musl

Artifact	Baseline	Commit	Change
/x86_64-alpine-linux-musl/lib/libdatadog_profiling.a	77.08 MB	77.08 MB	+0% (+24 B) 👌
/x86_64-alpine-linux-musl/lib/libdatadog_profiling.so	8.83 MB	8.83 MB	0% (0 B) 👌

x86_64-unknown-linux-gnu

Artifact	Baseline	Commit	Change
/x86_64-unknown-linux-gnu/lib/libdatadog_profiling.a	92.50 MB	92.50 MB	-0% (-48 B) 👌
/x86_64-unknown-linux-gnu/lib/libdatadog_profiling.so	10.74 MB	10.74 MB	0% (0 B) 👌

When tracers compute span metrics outside libdatadog, OTLP trace exports still need to mark the resource and direct Agent request so the Agent does not compute the same stats again. Use the tracer metadata flag in addition to libdatadog's native OTLP stats worker state.

github-actions Bot added the data-pipeline label Jul 16, 2026

bengl mentioned this pull request Jul 16, 2026

v0.18.0 DataDog/libdatadog-nodejs#180

Merged

bengl marked this pull request as ready for review July 16, 2026 15:44

bengl requested review from a team as code owners July 16, 2026 15:44

bengl requested review from vpellan and removed request for a team July 16, 2026 15:44

yannham approved these changes Jul 16, 2026

View reviewed changes

bengl force-pushed the bengl/otlp-client-computed-stats branch from a5515d2 to 1281505 Compare July 16, 2026 15:58

bengl force-pushed the bengl/otlp-client-computed-stats branch from 1281505 to 6356aee Compare July 16, 2026 16:37

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(trace-exporter): mark OTLP client-computed stats#2245

fix(trace-exporter): mark OTLP client-computed stats#2245
bengl wants to merge 1 commit into
mainfrom
bengl/otlp-client-computed-stats

bengl commented Jul 16, 2026

Uh oh!

github-actions Bot commented Jul 16, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jul 16, 2026 •

edited

Loading

Uh oh!

datadog-prod-us1-4 Bot commented Jul 16, 2026 •

edited by datadog-datadog-prod-us1-2 Bot

Loading

Uh oh!

pr-commenter Bot commented Jul 16, 2026 •

edited

Loading

Explanation

More details about the CI and significant changes

Group 1

Group 1

Uh oh!

yannham Jul 16, 2026

Uh oh!

dd-octo-sts Bot commented Jul 16, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

bengl commented Jul 16, 2026

What does this PR do?

Motivation

Additional Notes

How to test the change?

Uh oh!

github-actions Bot commented Jul 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

📚 Documentation Check Results

📦 libdd-data-pipeline - 1206 warning(s)

Uh oh!

github-actions Bot commented Jul 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔒 Cargo Deny Results

📦 libdd-data-pipeline - 3 error(s)

Uh oh!

datadog-prod-us1-4 Bot commented Jul 16, 2026 • edited by datadog-datadog-prod-us1-2 Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pr-commenter Bot commented Jul 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Benchmarks

Comparison

Explanation

More details about the CI and significant changes

scenario:trace_buffer/4_senders/no_delay

Candidate

Group 1

Baseline

Group 1

Uh oh!

yannham Jul 16, 2026

Choose a reason for hiding this comment

Uh oh!

dd-octo-sts Bot commented Jul 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Artifact Size Benchmark Report

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

github-actions Bot commented Jul 16, 2026 •

edited

Loading

📦 `libdd-data-pipeline` - 1206 warning(s)

github-actions Bot commented Jul 16, 2026 •

edited

Loading

📦 `libdd-data-pipeline` - 3 error(s)

datadog-prod-us1-4 Bot commented Jul 16, 2026 •

edited by datadog-datadog-prod-us1-2 Bot

Loading

pr-commenter Bot commented Jul 16, 2026 •

edited

Loading

dd-octo-sts Bot commented Jul 16, 2026 •

edited

Loading