fix(dogstatsd): Move the DSD prefix/filter component in front of the DSD enrich component by aqian01 · Pull Request #1575 · DataDog/saluki

aqian01 · 2026-05-04T17:34:18Z

Summary

Move the DogStatsD mapper before dsd_prefix_filter.

This makes ADP match the Core Agent order: map the metric name first, then apply statsd_metric_namespace and metric blocklist/filterlist rules. This fixes cases where blocklist entries for mapped metric names were not applied.

Change Type

Bug fix
New feature
Non-functional (chore, refactoring, docs)
Performance

How did you test this PR?

The new correctness test sends the same DogStatsD traffic through Core Agent and ADP, then compares the emitted metrics.

It generates two raw metric names:

mapper.blocklist.raw
mapper.blocklist.keep
The DogStatsD mapper rewrites them as:

mapper.blocklist.raw -> mapper.blocklist.mapped
mapper.blocklist.keep -> mapper.blocklist.allowed
The config blocklists only the mapped name:

statsd_metric_blocklist:
  - mapper.blocklist.mapped

So the expected result is:

mapper.blocklist.mapped is dropped after remapping
mapper.blocklist.allowed is still emitted

If ADP applies the blocklist before the mapper, it checks mapper.blocklist.raw, misses the blocklist, then remaps it to mapper.blocklist.mapped and emits it. The correctness test catches that because Core Agent drops it but ADP would leak it.

References

…nent to apply blocklist after remapping

pr-commenter · 2026-05-04T18:13:32Z

Binary Size Analysis (Agent Data Plane)

Target: 8965868 (baseline) vs a14cfcb (comparison) diff
Analysis Type: Stripped binaries (debug symbols excluded)
Baseline Size: 37.04 MiB
Comparison Size: 37.04 MiB
Size Change: -624 B (-0.00%)
Pass/Fail Threshold: +5%
Result: PASSED ✅

Changes by Module

Module	File Size	Symbols
`anon.2bef91b57997dcd336602b8dc2fe8990.2.llvm.18408503694074454322`	+1.48 KiB	1
`anon.622dc811fe301019123f4e07631bd6c7.254.llvm.5230852459485666564`	-1.48 KiB	1
`anon.8b81b8eb1ac445faa9e02aa301dced4e.1497.llvm.9961062273437274874`	+1.24 KiB	1
`anon.622dc811fe301019123f4e07631bd6c7.18.llvm.5230852459485666564`	-1.24 KiB	1
`anon.3fe086334a9f556d4cce3a92b5daae2f.31.llvm.6333889900533524017`	-1.17 KiB	1
`anon.42e15881a3807d9e08454c3c9df27af0.105.llvm.17600934669959620026`	+1.17 KiB	1
`anon.fec2ea894473053223f8a6b75ad6be44.168.llvm.4132632335714289129`	-1.15 KiB	1
`anon.4a57507c4069b300dc7151613f5e4bf3.34.llvm.8370593609202636011`	+1.15 KiB	1
`anon.4a57507c4069b300dc7151613f5e4bf3.412.llvm.8370593609202636011`	+812 B	1
`anon.4a57507c4069b300dc7151613f5e4bf3.412.llvm.3553081907174791088`	-811 B	1
`anon.facd3c337c8dcd330a569aa225085f1f.108.llvm.13032308475770315230`	+745 B	1
`anon.42e15881a3807d9e08454c3c9df27af0.306.llvm.12346359758138022109`	-744 B	1
`anon.ae03c1848ea9a743a5638bf33cf10665.1001.llvm.1832993645551364698`	+726 B	1
`anon.622dc811fe301019123f4e07631bd6c7.356.llvm.5230852459485666564`	-725 B	1
`anon.8b81b8eb1ac445faa9e02aa301dced4e.211.llvm.13941091674706208656`	-652 B	1
`anon.8b81b8eb1ac445faa9e02aa301dced4e.211.llvm.9961062273437274874`	+651 B	1
`anon.5cb9e416818518d6dd42723dba5b4056.92.llvm.9320009235808464563`	-643 B	1
`anon.4a57507c4069b300dc7151613f5e4bf3.107.llvm.8370593609202636011`	+642 B	1
`anon.8b81b8eb1ac445faa9e02aa301dced4e.944.llvm.9961062273437274874`	+642 B	1
`anon.9e23f8b9adb79cf5b15b5fcc24d10a90.415.llvm.10719386448939319901`	+642 B	1

Detailed Symbol Changes

    FILE SIZE        VM SIZE    
 --------------  -------------- 
  [NEW] +1.60Ki  [NEW]    +462    core::ptr::drop_in_place<alloc::boxed::Box<tokio::runtime::task::core::Cell<tokio::runtime::blocking::task::BlockingTask<tokio::fs::read::read<&std::path::PathBuf>::{{closure}}::{{closure}}>,tokio::runtime::blocking::schedule::BlockingSchedule>>>::hcdc9678dd5143f40
  [NEW] +1.48Ki  [NEW]     +76    anon.2bef91b57997dcd336602b8dc2fe8990.2.llvm.18408503694074454322
  [NEW] +1.24Ki  [NEW]     +91    anon.8b81b8eb1ac445faa9e02aa301dced4e.1497.llvm.9961062273437274874
  [NEW] +1.17Ki  [NEW]     +22    anon.42e15881a3807d9e08454c3c9df27af0.105.llvm.17600934669959620026
  [NEW] +1.15Ki  [NEW]     +92    anon.4a57507c4069b300dc7151613f5e4bf3.34.llvm.8370593609202636011
  [NEW] +1.09Ki  [NEW]    +315    core::ptr::drop_in_place<tokio::sync::mpsc::bounded::Permit<saluki_core::health::LivenessResponse>>::h5d6a395a3a192271
  [NEW]   +1015  [NEW]    +177    core::ptr::drop_in_place<tokio_stream::stream_ext::map::Map<tokio_stream::once::Once<containerd_protos::containerd_include::containerd::services::namespaces::v1::ListNamespacesRequest>,core::result::Result<containerd_protos::containerd_include::containerd::services::namespaces::v1::ListNamespacesRequest,tonic::status::Status>::Ok>>::h6fbef66dac65c78c
  +5.2%    +817  +5.2%    +817    _<chrono::format::formatting::DelayedFormat<I> as core::fmt::Display>::fmt::h52f0b306efca5f53
  [NEW]    +813  [NEW]     +29    core::error::Error::provide::hed2c01f29b70d88a
  [NEW]    +812  [NEW]     +84    anon.4a57507c4069b300dc7151613f5e4bf3.412.llvm.8370593609202636011
  -0.1%    -610  [ = ]       0    [1905 Others]
  [DEL]    -811  [DEL]     -84    anon.4a57507c4069b300dc7151613f5e4bf3.412.llvm.3553081907174791088
  [DEL]    -813  [DEL]     -29    core::error::Error::provide::h9955c78991d9d3fc
 -25.0%    -817 -25.9%    -817    chrono::format::formatting::write_rfc3339::hb315d0edc0939794
  [DEL]   -1015  [DEL]    -177    core::ptr::drop_in_place<tokio_stream::stream_ext::map::Map<tokio_stream::once::Once<datadog_protos::agent_include::datadog::remoteagent::v1::RefreshRemoteAgentRequest>,core::result::Result<datadog_protos::agent_include::datadog::remoteagent::v1::RefreshRemoteAgentRequest,tonic::status::Status>::Ok>>::h4d080964f8da579e
  [DEL] -1.10Ki  [DEL]    -315    core::ptr::drop_in_place<tokio::sync::mpsc::bounded::Permit<saluki_config::dynamic::event::ConfigUpdate>>::h5aec464b3def0b96
  [DEL] -1.15Ki  [DEL]     -92    anon.fec2ea894473053223f8a6b75ad6be44.168.llvm.4132632335714289129
  [DEL] -1.17Ki  [DEL]     -22    anon.3fe086334a9f556d4cce3a92b5daae2f.31.llvm.6333889900533524017
  [DEL] -1.24Ki  [DEL]     -91    anon.622dc811fe301019123f4e07631bd6c7.18.llvm.5230852459485666564
  [DEL] -1.48Ki  [DEL]     -76    anon.622dc811fe301019123f4e07631bd6c7.254.llvm.5230852459485666564
  [DEL] -1.60Ki  [DEL]    -462    core::ptr::drop_in_place<alloc::boxed::Box<tokio::runtime::task::core::Cell<tokio::runtime::blocking::task::BlockingTask<tokio::fs::read_to_string::read_to_string<&std::path::Path>::{{closure}}::{{closure}}>,tokio::runtime::blocking::schedule::BlockingSchedule>>>::h934106080d0e7e92
  -0.0%    -624  [ = ]       0    TOTAL

pr-commenter · 2026-05-04T18:29:27Z

Regression Detector (Agent Data Plane)

Regression Detector Results

Run ID: 8c7b8575-72ee-44b9-8a9e-13c2a26e2251

Baseline: 8965868
Comparison: a14cfcb
Diff

Optimization Goals: ✅ No significant changes detected

Experiments ignored for regressions

Regressions in experiments with settings containing erratic: true are ignored.

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	otlp_ingest_logs_5mb_cpu	% cpu utilization	+2.33	[-2.35, +7.01]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_throughput	ingress throughput	+0.01	[-0.12, +0.13]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_memory	memory utilization	-2.51	[-2.84, -2.18]	1	(metrics) (profiles) (logs)

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	dsd_uds_512kb_3k_contexts_cpu	% cpu utilization	+6.61	[-51.01, +64.24]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_ottl_transform_5mb_cpu	% cpu utilization	+2.33	[+0.41, +4.25]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_cpu	% cpu utilization	+2.33	[-2.35, +7.01]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_metrics_5mb_memory	memory utilization	+1.41	[+1.21, +1.62]	1	(metrics) (profiles) (logs)
➖	dsd_uds_500mb_3k_contexts_cpu	% cpu utilization	+1.02	[-0.29, +2.33]	1	(metrics) (profiles) (logs)
➖	dsd_uds_500mb_3k_contexts_throughput	ingress throughput	+0.44	[+0.23, +0.66]	1	(metrics) (profiles) (logs)
➖	dsd_uds_1mb_3k_contexts_memory	memory utilization	+0.26	[+0.11, +0.41]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_heavy	memory utilization	+0.17	[+0.05, +0.30]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_low	memory utilization	+0.13	[-0.03, +0.29]	1	(metrics) (profiles) (logs)
➖	dsd_uds_512kb_3k_contexts_memory	memory utilization	+0.07	[-0.07, +0.21]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_metrics_5mb_throughput	ingress throughput	+0.01	[-0.18, +0.20]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_throughput	ingress throughput	+0.01	[-0.12, +0.13]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_ottl_filtering_5mb_memory	memory utilization	+0.00	[-0.24, +0.24]	1	(metrics) (profiles) (logs)
➖	dsd_uds_512kb_3k_contexts_throughput	ingress throughput	+0.00	[-0.06, +0.06]	1	(metrics) (profiles) (logs)
➖	dsd_uds_10mb_3k_contexts_throughput	ingress throughput	+0.00	[-0.19, +0.19]	1	(metrics) (profiles) (logs)
➖	dsd_uds_1mb_3k_contexts_throughput	ingress throughput	-0.00	[-0.06, +0.06]	1	(metrics) (profiles) (logs)
➖	dsd_uds_100mb_3k_contexts_throughput	ingress throughput	-0.02	[-0.07, +0.04]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_5mb_throughput	ingress throughput	-0.04	[-0.12, +0.03]	1	(metrics) (profiles) (logs)
➖	dsd_uds_100mb_3k_contexts_memory	memory utilization	-0.10	[-0.25, +0.05]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_ottl_transform_5mb_throughput	ingress throughput	-0.12	[-0.20, -0.05]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_5mb_memory	memory utilization	-0.13	[-0.29, +0.03]	1	(metrics) (profiles) (logs)
➖	dsd_uds_10mb_3k_contexts_memory	memory utilization	-0.16	[-0.31, -0.00]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_ultraheavy	memory utilization	-0.16	[-0.30, -0.02]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_idle	memory utilization	-0.19	[-0.25, -0.14]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_ottl_filtering_5mb_throughput	ingress throughput	-0.25	[-0.32, -0.17]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_medium	memory utilization	-0.33	[-0.50, -0.16]	1	(metrics) (profiles) (logs)
➖	dsd_uds_500mb_3k_contexts_memory	memory utilization	-0.44	[-0.58, -0.30]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_ottl_transform_5mb_memory	memory utilization	-0.48	[-0.63, -0.33]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_ottl_filtering_5mb_cpu	% cpu utilization	-0.81	[-3.04, +1.42]	1	(metrics) (profiles) (logs)
➖	dsd_uds_100mb_3k_contexts_cpu	% cpu utilization	-1.63	[-7.00, +3.73]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_metrics_5mb_cpu	% cpu utilization	-1.88	[-7.77, +4.01]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_memory	memory utilization	-2.51	[-2.84, -2.18]	1	(metrics) (profiles) (logs)
➖	dsd_uds_10mb_3k_contexts_cpu	% cpu utilization	-3.81	[-32.48, +24.85]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_5mb_cpu	% cpu utilization	-4.12	[-6.15, -2.09]	1	(metrics) (profiles) (logs)
➖	dsd_uds_1mb_3k_contexts_cpu	% cpu utilization	-5.75	[-56.43, +44.94]	1	(metrics) (profiles) (logs)

Bounds Checks: ✅ Passed

perf	experiment	bounds_check_name	replicates_passed	observed_value	links
✅	quality_gates_rss_dsd_heavy	memory_usage	10/10	121.48MiB ≤ 140MiB	(metrics) (profiles) (logs)
✅	quality_gates_rss_dsd_low	memory_usage	10/10	40.41MiB ≤ 50MiB	(metrics) (profiles) (logs)
✅	quality_gates_rss_dsd_medium	memory_usage	10/10	60.48MiB ≤ 75MiB	(metrics) (profiles) (logs)
✅	quality_gates_rss_dsd_ultraheavy	memory_usage	10/10	179.50MiB ≤ 200MiB	(metrics) (profiles) (logs)
✅	quality_gates_rss_idle	memory_usage	10/10	27.59MiB ≤ 40MiB	(metrics) (profiles) (logs)

Explanation

Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%

Performance changes are noted in the perf column of each table:

✅ = significantly better comparison variant performance
❌ = significantly worse comparison variant performance
➖ = no significant change in performance

A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".

For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:

Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.
Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.
Its configuration does not mark it "erratic".

tobz

I think this makes sense to me if that's how we're doing it in the Core Agent.

Saying it out loud to try and not forget, but this is something that would be good to have a correctness test for... but I think we currently lack the ability to have lading spit out metrics with certain prefixes, which makes this infeasible to currently test.

Not a blocker to merging.

aqian01 · 2026-05-04T18:58:14Z

@tobz yup im working on adding the correctness test right now

tobz · 2026-05-04T19:21:34Z

@tobz yup im working on adding the correctness test right now

Ohhh, nice. I forgot about the support for specific metrics that got added to help with ASTA testing. 🙌🏻

…DSD enrich component (#1575) ## Summary  Move the DogStatsD mapper before dsd_prefix_filter. [Issue](https://datadoghq.atlassian.net/browse/DADP-67) This makes ADP match the Core Agent order: map the metric name first, then apply statsd_metric_namespace and metric blocklist/filterlist rules. This fixes cases where blocklist entries for mapped metric names were not applied. ## Change Type - [x] Bug fix - [ ] New feature - [ ] Non-functional (chore, refactoring, docs) - [ ] Performance ## How did you test this PR?  The new correctness test sends the same DogStatsD traffic through Core Agent and ADP, then compares the emitted metrics. It generates two raw metric names: `mapper.blocklist.raw` `mapper.blocklist.keep` The DogStatsD mapper rewrites them as: `mapper.blocklist.raw` -> `mapper.blocklist.mapped` `mapper.blocklist.keep` -> `mapper.blocklist.allowed` The config blocklists only the mapped name: ``` statsd_metric_blocklist: - mapper.blocklist.mapped ``` So the expected result is: `mapper.blocklist.mapped` is dropped after remapping `mapper.blocklist.allowed` is still emitted If ADP applies the blocklist before the mapper, it checks `mapper.blocklist.raw`, misses the blocklist, then remaps it to `mapper.blocklist.mapped` and emits it. The correctness test catches that because Core Agent drops it but ADP would leak it. ## References    Co-authored-by: andrew.qian <andrew.qian@datadoghq.com> b121f8f

Move the DSD prefix/filter component in front of the DSD enrich compo…

e71591f

…nent to apply blocklist after remapping

aqian01 changed the title ~~Fix(dogstatsd): Move the DSD prefix/filter component in front of the DSD enrich component~~ fix(dogstatsd): Move the DSD prefix/filter component in front of the DSD enrich component May 4, 2026

tobz added the type/bug Bug fixes. label May 4, 2026

tobz approved these changes May 4, 2026

View reviewed changes

add correctness test

a14cfcb

dd-octo-sts Bot added the area/test All things testing: unit/integration, correctness, SMP regression, etc. label May 4, 2026

aqian01 marked this pull request as ready for review May 4, 2026 19:12

aqian01 requested a review from a team as a code owner May 4, 2026 19:12

gh-worker-dd-devflow-36fce6 Bot added mergequeue-status: waiting mergequeue-status: queued mergequeue-status: in_progress and removed mergequeue-status: waiting mergequeue-status: queued labels May 4, 2026

gh-worker-dd-mergequeue-cf854d Bot merged commit b121f8f into main May 4, 2026
74 checks passed

gh-worker-dd-devflow-36fce6 Bot added mergequeue-status: done and removed mergequeue-status: in_progress labels May 4, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix(dogstatsd): Move the DSD prefix/filter component in front of the DSD enrich component#1575

fix(dogstatsd): Move the DSD prefix/filter component in front of the DSD enrich component#1575
gh-worker-dd-mergequeue-cf854d[bot] merged 2 commits into
mainfrom
andrewq/apply_blocklist_after_remapping

aqian01 commented May 4, 2026 •

edited

Loading

Uh oh!

pr-commenter Bot commented May 4, 2026 •

edited

Loading

Changes by Module

Detailed Symbol Changes

Uh oh!

pr-commenter Bot commented May 4, 2026 •

edited

Loading

Experiments ignored for regressions

Fine details of change detection per experiment

Bounds Checks: ✅ Passed

Explanation

Uh oh!

tobz left a comment

Uh oh!

aqian01 commented May 4, 2026

Uh oh!

tobz commented May 4, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

aqian01 commented May 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Change Type

How did you test this PR?

References

Uh oh!

pr-commenter Bot commented May 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Binary Size Analysis (Agent Data Plane)

Changes by Module

Detailed Symbol Changes

Uh oh!

pr-commenter Bot commented May 4, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Regression Detector (Agent Data Plane)

Regression Detector Results

Optimization Goals: ✅ No significant changes detected

Experiments ignored for regressions

Fine details of change detection per experiment

Bounds Checks: ✅ Passed

Explanation

Uh oh!

tobz left a comment

Choose a reason for hiding this comment

Uh oh!

aqian01 commented May 4, 2026

Uh oh!

tobz commented May 4, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

aqian01 commented May 4, 2026 •

edited

Loading

pr-commenter Bot commented May 4, 2026 •

edited

Loading

pr-commenter Bot commented May 4, 2026 •

edited

Loading