feat(stats)!: per-field cardinality limits by Eldolfin · Pull Request #2211 · DataDog/libdatadog

Eldolfin · 2026-07-08T12:07:16Z

What does this PR do?

Implement per-key cardinality limits to stats computation.

Also:

fix overflow key peer_tags: [] -> [tracer_blocked_value]
fix encode_grouped_stats meta with empty value: key: -> key (breaking change ?)

Motivation

CSS spec compliance.

Additional Notes

Todo:

save memory by storing value hashes only, u64 has enough values to make collisions rare and in case we still get a collision storing 1 extra key should be fine
telemetry (in a follow up feat(stats)!: add telemetry for per-field cardinality limits #2212)

How to test the change?

…n condition

This reverts commit a0bfe8c.

…f StatsExporter

it got introduced by mistake in 3d8ec6c

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

github-actions · 2026-07-08T12:09:18Z

📚 Documentation Check Results

⚠️ 3394 documentation warning(s) found

📦 `libdd-data-pipeline-ffi` - 1316 warning(s)

📦 `libdd-data-pipeline` - 1205 warning(s)

📦 `libdd-trace-stats` - 873 warning(s)

Updated: 2026-07-22 11:06:47 UTC | Commit: d850de6 | missing-docs job results

datadog-prod-us1-6 · 2026-07-08T12:10:47Z

Tests

🎉 All green!

🧪 All tests passed
❄️ No new flaky tests detected

🎯 Code Coverage (details)
• Patch Coverage: 97.45%
• Overall Coverage: 74.71% (+0.07%)

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

🔗 Commit SHA: 85c73e9 | Docs | Datadog PR Page | Give us feedback!}

github-actions · 2026-07-08T12:10:57Z

🔒 Cargo Deny Results

⚠️ 8 issue(s) found, showing only errors (advisories, bans, sources)

📦 `libdd-data-pipeline-ffi` - 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:78:1
   │
78 │ 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-data-pipeline-ffi v37.0.0
                     │   │   ├── libdd-data-pipeline-ffi v37.0.0 (*)
                     │   │   ├── libdd-shared-runtime v2.0.0
                     │   │   │   ├── libdd-data-pipeline v7.0.0 (*)
                     │   │   │   ├── libdd-data-pipeline-ffi v37.0.0 (*)
                     │   │   │   ├── 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 (*)
                     │   │   ├── (dev) libdd-telemetry v6.0.0 (*)
                     │   │   ├── libdd-trace-stats v6.0.0 (*)
                     │   │   └── libdd-trace-utils v9.0.0
                     │   │       ├── libdd-data-pipeline v7.0.0 (*)
                     │   │       ├── (dev) libdd-data-pipeline-ffi v37.0.0 (*)
                     │   │       ├── 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-common-ffi v37.0.0
                     │   │   └── libdd-data-pipeline-ffi v37.0.0 (*)
                     │   ├── 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:226:1
    │
226 │ 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](https://github.com/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-data-pipeline-ffi v37.0.0
      │   │   ├── libdd-data-pipeline-ffi v37.0.0 (*)
      │   │   ├── libdd-shared-runtime v2.0.0
      │   │   │   ├── libdd-data-pipeline v7.0.0 (*)
      │   │   │   ├── libdd-data-pipeline-ffi v37.0.0 (*)
      │   │   │   ├── 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 (*)
      │   │   ├── (dev) libdd-telemetry v6.0.0 (*)
      │   │   ├── libdd-trace-stats v6.0.0 (*)
      │   │   └── libdd-trace-utils v9.0.0
      │   │       ├── libdd-data-pipeline v7.0.0 (*)
      │   │       ├── (dev) libdd-data-pipeline-ffi v37.0.0 (*)
      │   │       ├── 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-common-ffi v37.0.0
      │   │   └── libdd-data-pipeline-ffi v37.0.0 (*)
      │   ├── 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 (*)
              ├── libdd-data-pipeline-ffi v37.0.0 (*)
              ├── (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:296:1
    │
296 │ 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
                  └── libdd-data-pipeline-ffi v37.0.0

advisories FAILED, bans ok, sources ok

📦 `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 (*)
                     │   │   ├── (dev) libdd-telemetry 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](https://github.com/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 (*)
      │   │   ├── (dev) libdd-telemetry 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

📦 `libdd-trace-stats` - 2 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:66:1
   │
66 │ 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-shared-runtime v2.0.0
                     │   │   │   ├── libdd-telemetry v6.0.0
                     │   │   │   │   └── libdd-trace-stats v6.0.0
                     │   │   │   └── libdd-trace-stats v6.0.0 (*)
                     │   │   ├── (dev) libdd-telemetry v6.0.0 (*)
                     │   │   ├── libdd-trace-stats v6.0.0 (*)
                     │   │   └── libdd-trace-utils v9.0.0
                     │   │       ├── 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-dogstatsd-client v4.0.0
                     │   │   └── 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-ddsketch v1.1.0
                     │   ├── libdd-telemetry v6.0.0 (*)
                     │   └── libdd-trace-stats v6.0.0 (*)
                     ├── (dev) libdd-trace-normalization v3.0.0
                     │   └── 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:198:1
    │
198 │ 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](https://github.com/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-shared-runtime v2.0.0
      │   │   │   ├── libdd-telemetry v6.0.0
      │   │   │   │   └── libdd-trace-stats v6.0.0
      │   │   │   └── libdd-trace-stats v6.0.0 (*)
      │   │   ├── (dev) libdd-telemetry v6.0.0 (*)
      │   │   ├── libdd-trace-stats v6.0.0 (*)
      │   │   └── libdd-trace-utils v9.0.0
      │   │       ├── 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-dogstatsd-client v4.0.0
      │   │   └── 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-ddsketch v1.1.0
      │   ├── libdd-telemetry v6.0.0 (*)
      │   └── libdd-trace-stats v6.0.0 (*)
      ├── (dev) libdd-trace-normalization v3.0.0
      │   └── 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
              ├── (dev) libdd-tinybytes v1.1.1 (*)
              └── libdd-trace-utils v9.0.0 (*)

advisories FAILED, bans ok, sources ok

Updated: 2026-07-22 11:08:01 UTC | Commit: d850de6 | dependency-check job results

Eldolfin · 2026-07-08T12:41:09Z

@codex review

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: a5a4786925

ℹ️ About Codex in GitHub

Your team has set up Codex to 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 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

dd-octo-sts · 2026-07-08T14:12:31Z

Artifact Size Benchmark Report

aarch64-alpine-linux-musl

Artifact	Baseline	Commit	Change
/aarch64-alpine-linux-musl/lib/libdatadog_profiling.a	88.18 MB	88.29 MB	+.12% (+112.58 KB) 🔍
/aarch64-alpine-linux-musl/lib/libdatadog_profiling.so	8.13 MB	8.13 MB	+0% (+48 B) 👌

aarch64-unknown-linux-gnu

Artifact	Baseline	Commit	Change
/aarch64-unknown-linux-gnu/lib/libdatadog_profiling.so	10.93 MB	10.93 MB	+.03% (+3.46 KB) 🔍
/aarch64-unknown-linux-gnu/lib/libdatadog_profiling.a	99.46 MB	99.57 MB	+.11% (+112.24 KB) 🔍

libdatadog-x64-windows

Artifact	Baseline	Commit	Change
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.dll	26.59 MB	26.62 MB	+.08% (+24.50 KB) 🔍
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.lib	89.18 KB	89.60 KB	+.47% (+430 B) 🔍
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.pdb	191.30 MB	191.40 MB	+.05% (+104.00 KB) 🔍
/libdatadog-x64-windows/debug/static/datadog_profiling_ffi.lib	1.04 GB	1.04 GB	--.03% (-427.41 KB) 💪
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.dll	8.66 MB	8.67 MB	+.10% (+9.00 KB) 🔍
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.lib	89.18 KB	89.60 KB	+.47% (+430 B) 🔍
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.pdb	25.36 MB	25.39 MB	+.12% (+32.00 KB) 🔍
/libdatadog-x64-windows/release/static/datadog_profiling_ffi.lib	50.55 MB	50.61 MB	+.10% (+54.83 KB) 🔍

libdatadog-x86-windows

Artifact	Baseline	Commit	Change
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.dll	23.16 MB	23.19 MB	+.09% (+23.50 KB) 🔍
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.lib	90.58 KB	91.00 KB	+.46% (+434 B) 🔍
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.pdb	195.94 MB	196.12 MB	+.08% (+176.00 KB) 🔍
/libdatadog-x86-windows/debug/static/datadog_profiling_ffi.lib	1.03 GB	1.03 GB	+.05% (+563.78 KB) 🔍
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.dll	6.68 MB	6.69 MB	+.15% (+10.50 KB) 🔍
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.lib	90.58 KB	91.00 KB	+.46% (+434 B) 🔍
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.pdb	27.26 MB	27.30 MB	+.11% (+32.00 KB) 🔍
/libdatadog-x86-windows/release/static/datadog_profiling_ffi.lib	48.13 MB	48.18 MB	+.11% (+54.26 KB) 🔍

x86_64-alpine-linux-musl

Artifact	Baseline	Commit	Change
/x86_64-alpine-linux-musl/lib/libdatadog_profiling.a	78.64 MB	78.74 MB	+.12% (+102.13 KB) 🔍
/x86_64-alpine-linux-musl/lib/libdatadog_profiling.so	9.05 MB	9.07 MB	+.17% (+16.06 KB) 🔍

x86_64-unknown-linux-gnu

Artifact	Baseline	Commit	Change
/x86_64-unknown-linux-gnu/lib/libdatadog_profiling.a	94.14 MB	94.24 MB	+.10% (+105.43 KB) 🔍
/x86_64-unknown-linux-gnu/lib/libdatadog_profiling.so	11.02 MB	11.03 MB	+.12% (+14.60 KB) 🔍

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d82ebfd172

ℹ️ About Codex in GitHub

Your team has set up Codex to 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 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

…alityLimitConfig binding

#2170

pr-commenter · 2026-07-10T12:55:45Z

Benchmarks

Comparison

Benchmark execution time: 2026-07-22 11:15:54

Comparing candidate commit 85c73e9 in PR branch oscarld/stats-per-key-cardinality-limit with baseline commit 63ecad5 in branch main.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 24 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 ----------------------------------'

Benchmark execution time: 2026-07-22 11:12:05

Comparing candidate commit 85c73e9 in PR branch oscarld/stats-per-key-cardinality-limit with baseline commit 63ecad5 in branch main.

Found 0 performance improvements and 1 performance regressions! Performance is the same for 2 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:concentrator/add_spans_to_concentrator

🟥 execution_time [+990.116µs; +997.265µs] or [+11.515%; +11.598%]

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	`85c73e9`	1784718237	oscarld/stats-per-key-cardinality-limit

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	56.283ms	56.504ms ± 0.124ms	56.479ms ± 0.066ms	56.551ms	56.740ms	56.872ms	57.073ms	1.05%	1.213	2.413	0.22%	0.009ms	1	200
trace_buffer/1_senders/10us_delay	throughput	15769.168op/s	15928.229op/s ± 34.879op/s	15935.121op/s ± 18.731op/s	15952.447op/s	15973.038op/s	15987.114op/s	15990.556op/s	0.35%	-1.193	2.337	0.22%	2.466op/s	1	200
trace_buffer/1_senders/1us_delay	execution_time	50.021ms	50.080ms ± 0.032ms	50.079ms ± 0.010ms	50.086ms	50.144ms	50.180ms	50.194ms	0.23%	1.049	2.030	0.06%	0.002ms	1	200
trace_buffer/1_senders/1us_delay	throughput	17930.602op/s	17971.420op/s ± 11.435op/s	17971.568op/s ± 3.576op/s	17977.009op/s	17988.800op/s	17990.569op/s	17992.300op/s	0.12%	-1.043	2.016	0.06%	0.809op/s	1	200
trace_buffer/1_senders/no_delay	execution_time	330.631µs	337.342µs ± 4.750µs	336.770µs ± 1.424µs	338.242µs	341.906µs	351.201µs	387.016µs	14.92%	6.230	59.225	1.40%	0.336µs	1	200
trace_buffer/1_senders/no_delay	throughput	2325486.484op/s	2668397.901op/s ± 34746.640op/s	2672447.993op/s ± 11347.974op/s	2683476.961op/s	2704779.908op/s	2716002.716op/s	2722068.859op/s	1.86%	-5.364	47.070	1.30%	2456.958op/s	1	200
trace_buffer/2_senders/10us_delay	execution_time	56.560ms	56.936ms ± 0.249ms	56.870ms ± 0.142ms	57.053ms	57.463ms	57.638ms	57.779ms	1.60%	1.057	0.664	0.44%	0.018ms	1	200
trace_buffer/2_senders/10us_delay	throughput	31153.056op/s	31615.263op/s ± 137.497op/s	31651.395op/s ± 79.298op/s	31711.122op/s	31783.049op/s	31817.237op/s	31824.751op/s	0.55%	-1.037	0.612	0.43%	9.723op/s	1	200
trace_buffer/2_senders/1us_delay	execution_time	50.020ms	50.111ms ± 0.036ms	50.108ms ± 0.019ms	50.123ms	50.185ms	50.232ms	50.282ms	0.35%	1.426	3.287	0.07%	0.003ms	1	200
trace_buffer/2_senders/1us_delay	throughput	35798.077op/s	35920.236op/s ± 25.852op/s	35922.762op/s ± 13.310op/s	35938.331op/s	35948.635op/s	35963.938op/s	35985.499op/s	0.17%	-1.419	3.259	0.07%	1.828op/s	1	200
trace_buffer/2_senders/no_delay	execution_time	846.988µs	899.560µs ± 20.549µs	899.125µs ± 14.365µs	913.469µs	928.859µs	947.963µs	995.087µs	10.67%	0.814	3.130	2.28%	1.453µs	1	200
trace_buffer/2_senders/no_delay	throughput	1808886.584op/s	2002001.298op/s ± 45044.657op/s	2001947.008op/s ± 31818.697op/s	2034128.671op/s	2077265.170op/s	2095067.107op/s	2125177.160op/s	6.16%	-0.535	2.088	2.24%	3185.138op/s	1	200
trace_buffer/4_senders/10us_delay	execution_time	57.144ms	57.459ms ± 0.151ms	57.446ms ± 0.102ms	57.565ms	57.715ms	57.792ms	57.908ms	0.81%	0.285	-0.334	0.26%	0.011ms	1	200
trace_buffer/4_senders/10us_delay	throughput	62167.092op/s	62653.371op/s ± 164.028op/s	62667.828op/s ± 111.754op/s	62763.238op/s	62902.881op/s	62953.152op/s	62999.088op/s	0.53%	-0.272	-0.346	0.26%	11.599op/s	1	200
trace_buffer/4_senders/1us_delay	execution_time	50.106ms	50.168ms ± 0.039ms	50.159ms ± 0.020ms	50.182ms	50.251ms	50.284ms	50.330ms	0.34%	1.363	1.989	0.08%	0.003ms	1	200
trace_buffer/4_senders/1us_delay	throughput	71528.419op/s	71758.500op/s ± 55.863op/s	71771.156op/s ± 27.910op/s	71795.734op/s	71823.776op/s	71838.975op/s	71847.844op/s	0.11%	-1.358	1.971	0.08%	3.950op/s	1	200
trace_buffer/4_senders/no_delay	execution_time	1.964ms	2.209ms ± 0.089ms	2.210ms ± 0.060ms	2.269ms	2.355ms	2.405ms	2.428ms	9.89%	-0.079	-0.186	4.01%	0.006ms	1	200
trace_buffer/4_senders/no_delay	throughput	1482405.697op/s	1632038.351op/s ± 66041.214op/s	1628979.554op/s ± 43790.760op/s	1674369.221op/s	1743118.476op/s	1799155.815op/s	1833250.816op/s	12.54%	0.304	0.021	4.04%	4669.819op/s	1	200
trace_buffer/8_senders/10us_delay	execution_time	57.547ms	57.858ms ± 0.218ms	57.797ms ± 0.112ms	57.952ms	58.286ms	58.424ms	59.095ms	2.25%	1.651	4.731	0.38%	0.015ms	1	200
trace_buffer/8_senders/10us_delay	throughput	121837.346op/s	124445.083op/s ± 465.222op/s	124573.156op/s ± 241.288op/s	124775.588op/s	124964.013op/s	125080.673op/s	125115.069op/s	0.44%	-1.607	4.435	0.37%	32.896op/s	1	200
trace_buffer/8_senders/1us_delay	execution_time	50.158ms	50.283ms ± 0.054ms	50.271ms ± 0.025ms	50.298ms	50.377ms	50.470ms	50.535ms	0.53%	1.637	3.796	0.11%	0.004ms	1	200
trace_buffer/8_senders/1us_delay	throughput	142474.976op/s	143189.195op/s ± 153.220op/s	143223.596op/s ± 70.492op/s	143284.460op/s	143357.822op/s	143389.107op/s	143547.286op/s	0.23%	-1.627	3.753	0.11%	10.834op/s	1	200
trace_buffer/8_senders/no_delay	execution_time	5.795ms	6.518ms ± 0.141ms	6.541ms ± 0.084ms	6.614ms	6.684ms	6.731ms	6.765ms	3.42%	-1.322	3.200	2.15%	0.010ms	1	200
trace_buffer/8_senders/no_delay	throughput	1064269.721op/s	1105230.024op/s ± 24610.632op/s	1100671.469op/s ± 14168.195op/s	1116419.834op/s	1151267.996op/s	1178832.978op/s	1242482.335op/s	12.88%	1.570	4.621	2.22%	1740.234op/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	[56.487ms; 56.521ms] or [-0.030%; +0.030%]	None	None	None
trace_buffer/1_senders/10us_delay	throughput	[15923.395op/s; 15933.063op/s] or [-0.030%; +0.030%]	None	None	None
trace_buffer/1_senders/1us_delay	execution_time	[50.075ms; 50.084ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/1_senders/1us_delay	throughput	[17969.835op/s; 17973.004op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/1_senders/no_delay	execution_time	[336.684µs; 338.001µs] or [-0.195%; +0.195%]	None	None	None
trace_buffer/1_senders/no_delay	throughput	[2663582.351op/s; 2673213.451op/s] or [-0.180%; +0.180%]	None	None	None
trace_buffer/2_senders/10us_delay	execution_time	[56.901ms; 56.970ms] or [-0.061%; +0.061%]	None	None	None
trace_buffer/2_senders/10us_delay	throughput	[31596.208op/s; 31634.319op/s] or [-0.060%; +0.060%]	None	None	None
trace_buffer/2_senders/1us_delay	execution_time	[50.106ms; 50.116ms] or [-0.010%; +0.010%]	None	None	None
trace_buffer/2_senders/1us_delay	throughput	[35916.653op/s; 35923.819op/s] or [-0.010%; +0.010%]	None	None	None
trace_buffer/2_senders/no_delay	execution_time	[896.712µs; 902.408µs] or [-0.317%; +0.317%]	None	None	None
trace_buffer/2_senders/no_delay	throughput	[1995758.542op/s; 2008244.055op/s] or [-0.312%; +0.312%]	None	None	None
trace_buffer/4_senders/10us_delay	execution_time	[57.439ms; 57.480ms] or [-0.036%; +0.036%]	None	None	None
trace_buffer/4_senders/10us_delay	throughput	[62630.638op/s; 62676.104op/s] or [-0.036%; +0.036%]	None	None	None
trace_buffer/4_senders/1us_delay	execution_time	[50.163ms; 50.174ms] or [-0.011%; +0.011%]	None	None	None
trace_buffer/4_senders/1us_delay	throughput	[71750.758op/s; 71766.242op/s] or [-0.011%; +0.011%]	None	None	None
trace_buffer/4_senders/no_delay	execution_time	[2.197ms; 2.222ms] or [-0.557%; +0.557%]	None	None	None
trace_buffer/4_senders/no_delay	throughput	[1622885.674op/s; 1641191.028op/s] or [-0.561%; +0.561%]	None	None	None
trace_buffer/8_senders/10us_delay	execution_time	[57.827ms; 57.888ms] or [-0.052%; +0.052%]	None	None	None
trace_buffer/8_senders/10us_delay	throughput	[124380.608op/s; 124509.558op/s] or [-0.052%; +0.052%]	None	None	None
trace_buffer/8_senders/1us_delay	execution_time	[50.276ms; 50.291ms] or [-0.015%; +0.015%]	None	None	None
trace_buffer/8_senders/1us_delay	throughput	[143167.960op/s; 143210.430op/s] or [-0.015%; +0.015%]	None	None	None
trace_buffer/8_senders/no_delay	execution_time	[6.498ms; 6.537ms] or [-0.299%; +0.299%]	None	None	None
trace_buffer/8_senders/no_delay	throughput	[1101819.227op/s; 1108640.821op/s] or [-0.309%; +0.309%]	None	None	None

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`85c73e9`	1784718237	oscarld/stats-per-key-cardinality-limit

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
two way interface	execution_time	15.075µs	15.427µs ± 0.210µs	15.402µs ± 0.131µs	15.544µs	15.701µs	15.877µs	16.771µs	8.88%	2.273	11.618	1.36%	0.015µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
two way interface	execution_time	[15.398µs; 15.456µs] or [-0.189%; +0.189%]	None	None	None

Group 2

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`85c73e9`	1784718237	oscarld/stats-per-key-cardinality-limit

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
concentrator/add_spans_to_concentrator	execution_time	9.567ms	9.593ms ± 0.017ms	9.589ms ± 0.011ms	9.602ms	9.622ms	9.633ms	9.682ms	0.97%	1.378	4.170	0.18%	0.001ms	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
concentrator/add_spans_to_concentrator	execution_time	[9.590ms; 9.595ms] or [-0.024%; +0.024%]	None	None	None

Group 3

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`85c73e9`	1784718237	oscarld/stats-per-key-cardinality-limit

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
write only interface	execution_time	1.058µs	1.075µs ± 0.005µs	1.074µs ± 0.004µs	1.080µs	1.082µs	1.083µs	1.083µs	0.84%	-0.561	-0.031	0.51%	0.000µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
write only interface	execution_time	[1.074µs; 1.076µs] or [-0.070%; +0.070%]	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	`63ecad5`	1784664248	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	56.299ms	56.494ms ± 0.111ms	56.482ms ± 0.064ms	56.535ms	56.669ms	56.874ms	57.162ms	1.20%	1.940	8.036	0.20%	0.008ms	1	200
trace_buffer/1_senders/10us_delay	throughput	15744.829op/s	15930.884op/s ± 31.070op/s	15934.307op/s ± 18.089op/s	15952.934op/s	15971.410op/s	15977.109op/s	15986.099op/s	0.33%	-1.903	7.797	0.19%	2.197op/s	1	200
trace_buffer/1_senders/1us_delay	execution_time	50.019ms	50.074ms ± 0.033ms	50.074ms ± 0.013ms	50.085ms	50.140ms	50.193ms	50.197ms	0.25%	1.276	2.772	0.07%	0.002ms	1	200
trace_buffer/1_senders/1us_delay	throughput	17929.202op/s	17973.432op/s ± 11.790op/s	17973.312op/s ± 4.812op/s	17981.274op/s	17988.966op/s	17991.723op/s	17993.040op/s	0.11%	-1.270	2.752	0.07%	0.834op/s	1	200
trace_buffer/1_senders/no_delay	execution_time	329.538µs	336.774µs ± 5.482µs	336.022µs ± 1.579µs	337.907µs	341.362µs	346.943µs	400.679µs	19.24%	8.157	90.911	1.62%	0.388µs	1	200
trace_buffer/1_senders/no_delay	throughput	2246188.104op/s	2673045.008op/s ± 38767.212op/s	2678395.755op/s ± 12646.507op/s	2690065.330op/s	2706369.717op/s	2724976.998op/s	2731099.875op/s	1.97%	-6.952	72.185	1.45%	2741.256op/s	1	200
trace_buffer/2_senders/10us_delay	execution_time	56.682ms	57.028ms ± 0.197ms	57.010ms ± 0.126ms	57.141ms	57.382ms	57.591ms	57.613ms	1.06%	0.737	0.260	0.35%	0.014ms	1	200
trace_buffer/2_senders/10us_delay	throughput	31242.733op/s	31563.811op/s ± 109.034op/s	31573.646op/s ± 69.914op/s	31641.758op/s	31711.409op/s	31741.238op/s	31756.037op/s	0.58%	-0.719	0.223	0.34%	7.710op/s	1	200
trace_buffer/2_senders/1us_delay	execution_time	50.036ms	50.110ms ± 0.032ms	50.106ms ± 0.018ms	50.122ms	50.176ms	50.213ms	50.226ms	0.24%	1.108	1.224	0.06%	0.002ms	1	200
trace_buffer/2_senders/1us_delay	throughput	35838.285op/s	35920.696op/s ± 23.171op/s	35924.035op/s ± 13.242op/s	35937.765op/s	35947.905op/s	35953.568op/s	35974.102op/s	0.14%	-1.105	1.214	0.06%	1.638op/s	1	200
trace_buffer/2_senders/no_delay	execution_time	859.520µs	905.544µs ± 17.666µs	905.827µs ± 11.879µs	917.959µs	928.170µs	936.598µs	1000.178µs	10.42%	0.438	3.355	1.95%	1.249µs	1	200
trace_buffer/2_senders/no_delay	throughput	1799680.357op/s	1988503.249op/s ± 38570.496op/s	1987135.166op/s ± 26078.978op/s	2012205.213op/s	2054941.231op/s	2083796.380op/s	2094192.107op/s	5.39%	-0.165	2.276	1.93%	2727.346op/s	1	200
trace_buffer/4_senders/10us_delay	execution_time	57.145ms	57.437ms ± 0.121ms	57.438ms ± 0.074ms	57.508ms	57.623ms	57.779ms	57.812ms	0.65%	0.097	0.198	0.21%	0.009ms	1	200
trace_buffer/4_senders/10us_delay	throughput	62271.182op/s	62677.967op/s ± 132.248op/s	62676.243op/s ± 81.270op/s	62759.238op/s	62890.158op/s	62986.035op/s	62997.603op/s	0.51%	-0.084	0.187	0.21%	9.351op/s	1	200
trace_buffer/4_senders/1us_delay	execution_time	50.090ms	50.169ms ± 0.037ms	50.162ms ± 0.015ms	50.178ms	50.247ms	50.282ms	50.410ms	0.49%	2.462	9.891	0.07%	0.003ms	1	200
trace_buffer/4_senders/1us_delay	throughput	71414.406op/s	71756.881op/s ± 53.121op/s	71766.996op/s ± 20.826op/s	71786.317op/s	71813.503op/s	71823.233op/s	71870.974op/s	0.14%	-2.449	9.791	0.07%	3.756op/s	1	200
trace_buffer/4_senders/no_delay	execution_time	2.013ms	2.304ms ± 0.094ms	2.300ms ± 0.061ms	2.369ms	2.454ms	2.493ms	2.557ms	11.15%	-0.098	-0.005	4.07%	0.007ms	1	200
trace_buffer/4_senders/no_delay	throughput	1408131.175op/s	1565400.240op/s ± 64433.691op/s	1565193.364op/s ± 41192.817op/s	1603789.968op/s	1670255.972op/s	1736726.599op/s	1788557.480op/s	14.27%	0.353	0.320	4.11%	4556.150op/s	1	200
trace_buffer/8_senders/10us_delay	execution_time	57.671ms	57.914ms ± 0.199ms	57.846ms ± 0.098ms	58.038ms	58.292ms	58.503ms	58.537ms	1.20%	1.165	0.619	0.34%	0.014ms	1	200
trace_buffer/8_senders/10us_delay	throughput	122998.870op/s	124324.146op/s ± 424.849op/s	124468.816op/s ± 211.453op/s	124640.156op/s	124775.504op/s	124819.302op/s	124847.190op/s	0.30%	-1.152	0.579	0.34%	30.041op/s	1	200
trace_buffer/8_senders/1us_delay	execution_time	50.201ms	50.277ms ± 0.046ms	50.266ms ± 0.025ms	50.300ms	50.368ms	50.425ms	50.468ms	0.40%	1.397	2.685	0.09%	0.003ms	1	200
trace_buffer/8_senders/1us_delay	throughput	142665.377op/s	143207.402op/s ± 130.395op/s	143237.082op/s ± 70.795op/s	143294.657op/s	143360.515op/s	143407.645op/s	143423.703op/s	0.13%	-1.390	2.654	0.09%	9.220op/s	1	200
trace_buffer/8_senders/no_delay	execution_time	5.302ms	6.329ms ± 0.176ms	6.355ms ± 0.099ms	6.459ms	6.526ms	6.569ms	6.584ms	3.61%	-1.756	5.488	2.78%	0.012ms	1	200
trace_buffer/8_senders/no_delay	throughput	1093568.395op/s	1138629.095op/s ± 33575.764op/s	1133016.020op/s ± 17629.388op/s	1149672.359op/s	1208409.470op/s	1237387.944op/s	1357873.033op/s	19.85%	2.197	8.852	2.94%	2374.165op/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	[56.479ms; 56.510ms] or [-0.027%; +0.027%]	None	None	None
trace_buffer/1_senders/10us_delay	throughput	[15926.578op/s; 15935.190op/s] or [-0.027%; +0.027%]	None	None	None
trace_buffer/1_senders/1us_delay	execution_time	[50.069ms; 50.078ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/1_senders/1us_delay	throughput	[17971.798op/s; 17975.066op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/1_senders/no_delay	execution_time	[336.014µs; 337.533µs] or [-0.226%; +0.226%]	None	None	None
trace_buffer/1_senders/no_delay	throughput	[2667672.245op/s; 2678417.771op/s] or [-0.201%; +0.201%]	None	None	None
trace_buffer/2_senders/10us_delay	execution_time	[57.001ms; 57.055ms] or [-0.048%; +0.048%]	None	None	None
trace_buffer/2_senders/10us_delay	throughput	[31548.700op/s; 31578.922op/s] or [-0.048%; +0.048%]	None	None	None
trace_buffer/2_senders/1us_delay	execution_time	[50.106ms; 50.115ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/1us_delay	throughput	[35917.485op/s; 35923.908op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/no_delay	execution_time	[903.096µs; 907.992µs] or [-0.270%; +0.270%]	None	None	None
trace_buffer/2_senders/no_delay	throughput	[1983157.749op/s; 1993848.749op/s] or [-0.269%; +0.269%]	None	None	None
trace_buffer/4_senders/10us_delay	execution_time	[57.420ms; 57.454ms] or [-0.029%; +0.029%]	None	None	None
trace_buffer/4_senders/10us_delay	throughput	[62659.638op/s; 62696.295op/s] or [-0.029%; +0.029%]	None	None	None
trace_buffer/4_senders/1us_delay	execution_time	[50.164ms; 50.175ms] or [-0.010%; +0.010%]	None	None	None
trace_buffer/4_senders/1us_delay	throughput	[71749.519op/s; 71764.243op/s] or [-0.010%; +0.010%]	None	None	None
trace_buffer/4_senders/no_delay	execution_time	[2.291ms; 2.317ms] or [-0.565%; +0.565%]	None	None	None
trace_buffer/4_senders/no_delay	throughput	[1556470.351op/s; 1574330.130op/s] or [-0.570%; +0.570%]	None	None	None
trace_buffer/8_senders/10us_delay	execution_time	[57.886ms; 57.941ms] or [-0.048%; +0.048%]	None	None	None
trace_buffer/8_senders/10us_delay	throughput	[124265.266op/s; 124383.026op/s] or [-0.047%; +0.047%]	None	None	None
trace_buffer/8_senders/1us_delay	execution_time	[50.270ms; 50.283ms] or [-0.013%; +0.013%]	None	None	None
trace_buffer/8_senders/1us_delay	throughput	[143189.331op/s; 143225.474op/s] or [-0.013%; +0.013%]	None	None	None
trace_buffer/8_senders/no_delay	execution_time	[6.304ms; 6.353ms] or [-0.386%; +0.386%]	None	None	None
trace_buffer/8_senders/no_delay	throughput	[1133975.817op/s; 1143282.373op/s] or [-0.409%; +0.409%]	None	None	None

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`63ecad5`	1784664248	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
two way interface	execution_time	14.880µs	15.315µs ± 0.165µs	15.307µs ± 0.115µs	15.427µs	15.613µs	15.745µs	15.858µs	3.60%	0.384	0.484	1.07%	0.012µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
two way interface	execution_time	[15.292µs; 15.338µs] or [-0.149%; +0.149%]	None	None	None

Group 2

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`63ecad5`	1784664248	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
concentrator/add_spans_to_concentrator	execution_time	8.569ms	8.599ms ± 0.020ms	8.593ms ± 0.012ms	8.609ms	8.642ms	8.657ms	8.664ms	0.82%	1.139	0.940	0.23%	0.001ms	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
concentrator/add_spans_to_concentrator	execution_time	[8.596ms; 8.602ms] or [-0.031%; +0.031%]	None	None	None

Group 3

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`63ecad5`	1784664248	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
write only interface	execution_time	1.070µs	1.087µs ± 0.007µs	1.089µs ± 0.004µs	1.092µs	1.098µs	1.099µs	1.100µs	0.99%	-0.433	-0.589	0.63%	0.000µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
write only interface	execution_time	[1.087µs; 1.088µs] or [-0.088%; +0.088%]	None	None	None

VianneyRuhlmann

LGTM, although I think we should make sure that this is shipped in the same release as the telemetry PR

…-cardinality-limit

…2170) # What does this PR do? - Add additional metric tags to the stats aggregation key. For each configured key, the matching span meta tag is included in the key and populates `ClientGroupedStats.additional_metric_tags`. - Limit the number of keys for `additional_metric_tags` to 4, not configurable. - Limit the maximum length of individual additional_metric_tags values to 200 characters, not configurable. Values exceeding this are replaced with `tracer_blocked_value`. # Motivation - Allow Serverless Compatibility Layer to send additional metric tags on trace stats. See [RFC](https://datadoghq.atlassian.net/wiki/spaces/APM/pages/6482919540/PENDING+Span-Derived+Primary+Tags+-+V1). - DataDog/serverless-components#140 to follow. - https://datadoghq.atlassian.net/browse/SVLS-8787 # Additional Notes Additional metric tags still need to be implemented in libdd-data-pipeline. Omitted from this PR since the goal of this PR is to support additional metric tags tags for Serverless without affecting other teams. https://github.com/DataDog/libdatadog/blob/42e3296aa3fa76749caf5d96b5bbf1ff2b1913b6/libdd-data-pipeline/src/trace_exporter/stats.rs#L146 Per-field cardinality limit for additional metric tags will be implemented in a following PR, #2211. - Limit the number of distinct aggregation entries per bucket that carry additional metric tags to 100 by default, configurable via `additional_metric_tags_max_entries`. Once exceeded, new entries have their tag values masked to `tracer_blocked_value`. --- Implementing additional metric tags instead of span derived primary tags. See previous PR for span derived primary tags - #1815. # How to test the change? - Unit tests - Deploy to Azure Functions with the following environment variables and validate that additional tags appear on trace metrics * `DD_TAGS: custom.primary:val,workload:azure_functions` * `DD_TRACE_EXPERIMENTAL_FEATURES_ENABLED: true` * `DD_TRACE_STATS_ADDITIONAL_TAGS: custom.primary,workload` <img width="685" height="411" alt="Screenshot 2026-07-06 at 3 39 47 PM" src="https://github.com/user-attachments/assets/b91495b6-11aa-4051-922f-63655666c4e5" /> Co-authored-by: duncan.harvey <duncan.harvey@datadoghq.com>

…-cardinality-limit fix: bad merge

Eldolfin · 2026-07-22T09:49:15Z

@codex review

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 2906b45c52

ℹ️ About Codex in GitHub

Your team has set up Codex to 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 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Eldolfin and others added 14 commits July 7, 2026 11:41

fix: attach obfuscation flag to stats buckets, fix obfuscation versio…

52710cf

…n condition

fix: fmt

a62a150

fix: flush buckets which have the same obfuscation indicator together

8f65b1d

fix(sidecar): remove useless stats-obfuscation feature

a0bfe8c

Revert "fix(sidecar): remove useless stats-obfuscation feature"

6c6f058

This reverts commit a0bfe8c.

fix: outdated comment, remove metadata return from otlp flush

a44467a

fix: tests lints

3113a7e

fix: local review suggestions

909d654

fix: fmt

85eaf0c

fix(test): put back obfuscation enabled in SpanConcentrator instead o…

05d2364

…f StatsExporter

fix: remove unused file results.xml

ed0277a

it got introduced by mistake in 3d8ec6c

fix error message StateExporter -> StatsExporter

888e56c

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

fix nit comment

9d91a3c

refacto: cleaner flush result struct, simplify span obfuscation path

2342ce1

github-actions Bot added the data-pipeline label Jul 8, 2026

Eldolfin force-pushed the oscarld/stats-per-key-cardinality-limit branch from a5a4786 to 2845fa8 Compare July 8, 2026 12:50

Eldolfin changed the base branch from main to oscarld/fix-css-obfuscation-logic July 8, 2026 12:51

Eldolfin force-pushed the oscarld/stats-per-key-cardinality-limit branch from 2845fa8 to fca0f65 Compare July 8, 2026 12:52

chatgpt-codex-connector Bot reviewed Jul 8, 2026

View reviewed changes

Comment thread libdd-trace-stats/src/span_concentrator/aggregation.rs Outdated

Comment thread libdd-data-pipeline/src/trace_exporter/builder.rs

Comment thread libdd-trace-stats/src/span_concentrator/aggregation.rs Outdated

Eldolfin marked this pull request as ready for review July 8, 2026 15:15

Eldolfin requested review from a team as code owners July 8, 2026 15:15

chatgpt-codex-connector Bot reviewed Jul 8, 2026

View reviewed changes

Comment thread libdd-data-pipeline-ffi/src/trace_exporter.rs

Comment thread libdd-trace-stats/src/span_concentrator/aggregation.rs

feat: send obfuscated/unobfuscated stats concurrently

2d4eebc

VianneyRuhlmann reviewed Jul 9, 2026

View reviewed changes

Comment thread libdd-trace-stats/src/span_concentrator/mod.rs Outdated

Comment thread libdd-trace-stats/src/span_concentrator/aggregation.rs Outdated

Comment thread libdd-trace-stats/src/span_concentrator/aggregation.rs Outdated

Comment thread libdd-trace-stats/src/span_concentrator/mod.rs

Eldolfin added 6 commits July 10, 2026 14:14

fix: fmt

1c46a80

fix(ffi): add libdd-trace-stats to cbindgen config to generate Cardin…

04befd7

…alityLimitConfig binding

fix: inline DEFAULT_MAX_ENTRIES_PER_BUCKET

74f105a

fix: link span derived primary tags ticket and pr

edf1e0c

#2170

fix: avoid useless re-hashes

5cedcf4

fix: warn on any cardinality limit = 0

83043a4

Eldolfin force-pushed the oscarld/stats-per-key-cardinality-limit branch from efe280f to 83043a4 Compare July 10, 2026 12:14

fix: fmt

39427ce

Base automatically changed from oscarld/fix-css-obfuscation-logic to main July 10, 2026 16:26

gh-worker-dd-mergequeue-cf854d Bot requested review from a team as code owners July 10, 2026 16:26

gh-worker-dd-mergequeue-cf854d Bot requested review from mabdinur and removed request for a team July 10, 2026 16:26

Eldolfin mentioned this pull request Jul 13, 2026

feat(stats)!: implement additional metric tags in libdd-trace-stats #2170

Merged

VianneyRuhlmann approved these changes Jul 20, 2026

View reviewed changes

Comment thread libdd-data-pipeline-ffi/src/trace_exporter.rs

Eldolfin added 2 commits July 20, 2026 18:00

feat: add function to get default cardinality limit config

a14a2b6

Merge remote-tracking branch 'origin/main' into oscarld/stats-per-key…

45e3b60

…-cardinality-limit

gh-worker-ownership-write-b05516 Bot removed the request for review from a team July 21, 2026 09:55

fix: bad merge lints

a1c321a

Eldolfin added 4 commits July 22, 2026 10:44

fix: apply configured limits to OTLP stats

4b3981f

Merge remote-tracking branch 'origin/main' into oscarld/stats-per-key…

909fb50

…-cardinality-limit fix: bad merge

explain HashSet of hashes reasoning

854ef55

implement additional_metrics_tags field cardinality limit

2906b45

chatgpt-codex-connector Bot reviewed Jul 22, 2026

View reviewed changes

Comment thread libdd-trace-stats/src/span_concentrator/mod.rs

Eldolfin changed the title ~~feat(stats)!: per-key cardinality limits~~ feat(stats)!: per-field cardinality limits Jul 22, 2026

fix: missing resource cardinality limit = 0 warn

85c73e9

Uh oh!

Conversation

Eldolfin commented Jul 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Motivation

Additional Notes

How to test the change?

Uh oh!

github-actions Bot commented Jul 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

📚 Documentation Check Results

📦 libdd-data-pipeline-ffi - 1316 warning(s)

📦 libdd-data-pipeline - 1205 warning(s)

📦 libdd-trace-stats - 873 warning(s)

Uh oh!

datadog-prod-us1-6 Bot commented Jul 8, 2026 • edited by datadog-prod-us1-5 Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Jul 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔒 Cargo Deny Results

📦 libdd-data-pipeline-ffi - 3 error(s)

📦 libdd-data-pipeline - 3 error(s)

📦 libdd-trace-stats - 2 error(s)

Uh oh!

Eldolfin commented Jul 8, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

dd-octo-sts Bot commented Jul 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Artifact Size Benchmark Report

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

pr-commenter Bot commented Jul 10, 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

Explanation

More details about the CI and significant changes

scenario:concentrator/add_spans_to_concentrator

Candidate

Group 1

Group 1

Group 2

Group 3

Baseline

Group 1

Group 1

Group 2

Group 3

Uh oh!

VianneyRuhlmann left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Eldolfin commented Jul 22, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

Eldolfin commented Jul 8, 2026 •

edited

Loading

github-actions Bot commented Jul 8, 2026 •

edited

Loading

📦 `libdd-data-pipeline-ffi` - 1316 warning(s)

📦 `libdd-data-pipeline` - 1205 warning(s)

📦 `libdd-trace-stats` - 873 warning(s)

datadog-prod-us1-6 Bot commented Jul 8, 2026 •

edited by datadog-prod-us1-5 Bot

Loading

github-actions Bot commented Jul 8, 2026 •

edited

Loading

📦 `libdd-data-pipeline-ffi` - 3 error(s)

📦 `libdd-data-pipeline` - 3 error(s)

📦 `libdd-trace-stats` - 2 error(s)

dd-octo-sts Bot commented Jul 8, 2026 •

edited

Loading

pr-commenter Bot commented Jul 10, 2026 •

edited

Loading