Skip to content

[Profiler] Add support for ARM64#8338

Merged
gleocadie merged 63 commits into
masterfrom
gleocadie/add-frame-based-pointer-unwinding-for-arm64
May 15, 2026
Merged

[Profiler] Add support for ARM64#8338
gleocadie merged 63 commits into
masterfrom
gleocadie/add-frame-based-pointer-unwinding-for-arm64

Conversation

@gleocadie

@gleocadie gleocadie commented Mar 19, 2026

Copy link
Copy Markdown
Collaborator

Summary of changes

Add support for .NET profiler on aarch64.

Reason for change

Customers ask :)

Implementation details

The implementation relies on the ManagedCodeCache. We added a new unwinder HybridUnwinder which first uses libunwind to get passed the native frame. Once we hit a managed frame (thanks to ManagedCodeCache::IsManaged), we walk the callstack using the FP-chain. .NET Jit is known to push the frame pointer on the stack.

Additional:

  • ManagedCodeCache::IsManaged returns an std::optional<bool> because in some contention case, we may not know for sure if an instruction pointer is native or managed. In case we do not know, we implemented a retry mechanism. In the if we still do not know, we stop the unwinding to avoid crashing the app.
  • UnwindingRecorder class is enabled and used only if the Debug log is enabled. For now, we do not write the recording into a file. This will be done in a later PR.

Test coverage

Using the same tests we have + minor adjustments:
Due to contention between the ManagedCodeCache::Worker and the unwinder, at startup we may have truncated callstack. This is fine for. A rework of the ManagedCodeCache will be done to remove that limitation.

This fact is taken into account in the assertions.

Other details

To enable profiler on ARM64, we have a this env var DD_INTERNAL_PROFILING_ENABLED_ARM64 which must set to 1.

@github-actions github-actions Bot added the area:profiler Issues related to the continous-profiler label Mar 19, 2026
@pr-commenter

pr-commenter Bot commented Mar 19, 2026

Copy link
Copy Markdown

Benchmarks

Benchmark execution time: 2026-05-11 09:05:33

Comparing candidate commit 3d2d5b9 in PR branch gleocadie/add-frame-based-pointer-unwinding-for-arm64 with baseline commit e048c61 in branch master.

Some scenarios are present only in baseline or only in candidate runs. If you didn't create or remove some scenarios in your branch, this maybe a sign of crashed benchmarks 💥💥💥
Check Gitlab CI job log to find if any benchmark has crashed.

Scenarios present only in baseline:

  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_AddEvent_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_UpdateName_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan net472
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_SetStatus_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_SetAttributes_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_SetAttributes_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_SetStatus_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_SetStatus_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_SetAttributes_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_AddEvent_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_AddEvent_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_AddEvent_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_AddEvent_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_SetStatus_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_AddEvent_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_GetContext_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_SetStatus_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_UpdateName_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_GetContext_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_UpdateName_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_UpdateName_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_RecordException_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_UpdateName_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_SetAttributes_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_GetContext_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_RecordException_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_SetAttributes_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_GetContext_Sampled netcoreapp3.1
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_SetAttributes_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_UpdateName_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_GetContext_Sampled net472
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_RecordException_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.ActivityBenchmark.StartSpan_GetContext_Sampled net6.0
  • Benchmarks.OpenTelemetry.Api.Trace.TelemetrySpanBenchmark.StartSpan_SetStatus_Sampled netcoreapp3.1

Found 4 performance improvements and 2 performance regressions! Performance is the same for 48 metrics, 18 unstable metrics, 88 known flaky benchmarks, 38 flaky benchmarks without significant changes.

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:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TracerBenchmark.StartActiveSpan net6.0

  • 🟩 allocated_mem [-144 bytes; -143 bytes] or [-9.188%; -9.180%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TracerBenchmark.StartSpan_SetActive net6.0

  • 🟩 allocated_mem [-144 bytes; -143 bytes] or [-7.321%; -7.312%]

scenario:Benchmarks.Trace.HttpClientBenchmark.SendAsync net6.0

  • 🟥 throughput [-70048.017op/s; -62218.451op/s] or [-47.585%; -42.266%]
  • 🟩 execution_time [-41.880ms; -24.348ms] or [-20.783%; -12.083%]

scenario:Benchmarks.Trace.HttpClientBenchmark.SendAsync netcoreapp3.1

  • 🟩 execution_time [-97.778ms; -95.948ms] or [-48.830%; -47.916%]

scenario:Benchmarks.Trace.NLogBenchmark.EnrichedLog net6.0

  • 🟥 throughput [-60639.020op/s; -44509.603op/s] or [-30.405%; -22.317%]

Known flaky benchmarks

These benchmarks are marked as flaky and will not trigger a failure. Modify FLAKY_BENCHMARKS_REGEX to control which benchmarks are marked as flaky.

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan net6.0

  • unstable execution_time [-1.790ms; +19.910ms] or [-1.369%; +15.225%]
  • unstable throughput [-20719.769op/s; +2791.309op/s] or [-11.349%; +1.529%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan netcoreapp3.1

  • unstable execution_time [-37.235ms; -12.390ms] or [-32.858%; -10.934%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_AddEvent_Sampled net6.0

  • unstable execution_time [+3.518ms; +21.764ms] or [+2.769%; +17.132%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_AddEvent_Sampled netcoreapp3.1

  • unstable execution_time [-34.763ms; -10.156ms] or [-31.148%; -9.100%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_GetContext_Sampled net6.0

  • unstable execution_time [-37.239ms; -3.400ms] or [-25.049%; -2.287%]
  • unstable throughput [+2056.407op/s; +25385.719op/s] or [+1.225%; +15.121%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_SetAttributes_Sampled net6.0

  • unstable execution_time [-17.228ms; -1.913ms] or [-11.542%; -1.282%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_SetAttributes_Sampled netcoreapp3.1

  • unstable execution_time [-58.967ms; -29.207ms] or [-43.357%; -21.475%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_SetStatus_Sampled net6.0

  • unstable execution_time [+17.789ms; +70.275ms] or [+11.685%; +46.161%]
  • unstable throughput [-53650.624op/s; -17871.767op/s] or [-30.879%; -10.286%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_SetStatus_Sampled netcoreapp3.1

  • unstable execution_time [-58.061ms; -27.692ms] or [-43.778%; -20.880%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_UpdateName_Sampled net6.0

  • unstable execution_time [-39.009ms; +1.638ms] or [-23.038%; +0.967%]
  • unstable throughput [-5188.931op/s; +26910.201op/s] or [-3.167%; +16.424%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_UpdateName_Sampled netcoreapp3.1

  • unstable execution_time [-37.961ms; -13.169ms] or [-33.598%; -11.656%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan net6.0

  • 🟥 allocated_mem [+143 bytes; +144 bytes] or [+10.108%; +10.117%]
  • unstable execution_time [-31.630ms; +13.344ms] or [-17.590%; +7.421%]
  • unstable throughput [-14659.828op/s; +16434.570op/s] or [-10.204%; +11.440%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan netcoreapp3.1

  • unstable execution_time [+7.877ms; +32.005ms] or [+8.575%; +34.841%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_AddEvent_Sampled net6.0

  • unstable execution_time [-7.105ms; +16.316ms] or [-5.112%; +11.738%]
  • unstable throughput [-15690.323op/s; +1376.009op/s] or [-10.926%; +0.958%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_GetContext_Sampled net6.0

  • unstable execution_time [-28.025ms; -10.650ms] or [-19.774%; -7.515%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_RecordException_Sampled net6.0

  • unstable execution_time [-6.999ms; +22.035ms] or [-5.028%; +15.829%]
  • unstable throughput [-40097.045op/s; -18661.125op/s] or [-30.845%; -14.355%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_RecordException_Sampled netcoreapp3.1

  • unstable execution_time [-19.876ms; +15.906ms] or [-17.692%; +14.157%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_SetAttributes_Sampled net6.0

  • unstable execution_time [-64.099ms; -30.131ms] or [-34.772%; -16.345%]
  • unstable throughput [+13615.484op/s; +29430.066op/s] or [+13.049%; +28.205%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_SetAttributes_Sampled netcoreapp3.1

  • unstable execution_time [+30.033ms; +60.071ms] or [+33.333%; +66.671%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_SetStatus_Sampled net6.0

  • unstable execution_time [-32.581ms; -4.444ms] or [-17.395%; -2.373%]
  • unstable throughput [+19971.082op/s; +38874.116op/s] or [+17.244%; +33.565%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_UpdateName_Sampled net6.0

  • unstable execution_time [+4.647ms; +23.122ms] or [+3.693%; +18.375%]

scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_UpdateName_Sampled netcoreapp3.1

  • unstable execution_time [-60.126ms; -29.341ms] or [-44.957%; -21.938%]

scenario:Benchmarks.Trace.ActivityBenchmark.StartStopWithChild net472

  • 🟥 throughput [-9084.357op/s; -7967.771op/s] or [-10.771%; -9.447%]

scenario:Benchmarks.Trace.ActivityBenchmark.StartStopWithChild net6.0

  • unstable execution_time [-81.703ms; -57.241ms] or [-40.762%; -28.558%]
  • unstable throughput [-36654.708op/s; -22997.491op/s] or [-30.810%; -19.330%]

scenario:Benchmarks.Trace.ActivityBenchmark.StartStopWithChild netcoreapp3.1

  • unstable execution_time [-70.758ms; -43.060ms] or [-35.589%; -21.658%]
  • 🟥 throughput [-6779.358op/s; -5458.115op/s] or [-6.893%; -5.550%]

scenario:Benchmarks.Trace.AgentWriterBenchmark.WriteAndFlushEnrichedTraces net472

  • 🟥 execution_time [+328.139ms; +342.576ms] or [+162.834%; +169.998%]
  • 🟥 throughput [-54.471op/s; -41.780op/s] or [-9.800%; -7.517%]

scenario:Benchmarks.Trace.AgentWriterBenchmark.WriteAndFlushEnrichedTraces net6.0

  • 🟥 execution_time [+98.741ms; +100.481ms] or [+78.012%; +79.386%]
  • 🟩 throughput [+87.350op/s; +93.780op/s] or [+11.517%; +12.365%]

scenario:Benchmarks.Trace.AgentWriterBenchmark.WriteAndFlushEnrichedTraces netcoreapp3.1

  • 🟥 execution_time [+84.151ms; +85.460ms] or [+74.471%; +75.629%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleMoreComplexBody net472

  • 🟥 allocated_mem [+1.308KB; +1.308KB] or [+27.528%; +27.540%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleMoreComplexBody net6.0

  • 🟥 allocated_mem [+439 bytes; +440 bytes] or [+9.299%; +9.310%]
  • 🟩 execution_time [-37.827ms; -23.383ms] or [-17.666%; -10.921%]
  • 🟥 throughput [-37243.191op/s; -27096.783op/s] or [-27.185%; -19.779%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleMoreComplexBody netcoreapp3.1

  • 🟥 allocated_mem [+1.272KB; +1.272KB] or [+27.500%; +27.510%]
  • 🟩 execution_time [-63.824ms; -43.613ms] or [-30.393%; -20.768%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleSimpleBody net472

  • 🟥 allocated_mem [+1.307KB; +1.307KB] or [+105.743%; +105.758%]
  • 🟥 throughput [-291169.177op/s; -281646.557op/s] or [-29.730%; -28.757%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleSimpleBody net6.0

  • 🟥 allocated_mem [+439 bytes; +440 bytes] or [+35.945%; +35.954%]
  • unstable execution_time [-90.529ms; -66.254ms] or [-40.372%; -29.546%]
  • unstable throughput [-249771.188op/s; -141593.448op/s] or [-26.683%; -15.127%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleSimpleBody netcoreapp3.1

  • 🟥 allocated_mem [+1.272KB; +1.272KB] or [+105.288%; +105.304%]
  • unstable execution_time [-77.579ms; -54.734ms] or [-38.724%; -27.321%]
  • 🟥 throughput [-123138.107op/s; -106240.828op/s] or [-17.693%; -15.265%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorMoreComplexBody net6.0

  • 🟩 execution_time [-43.333ms; -23.768ms] or [-21.864%; -11.992%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorMoreComplexBody netcoreapp3.1

  • unstable execution_time [-49.437ms; -29.595ms] or [-25.205%; -15.089%]
  • 🟩 throughput [+10177.331op/s; +12902.225op/s] or [+8.108%; +10.278%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorSimpleBody net6.0

  • 🟩 execution_time [-70.893ms; -54.066ms] or [-35.052%; -26.732%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorSimpleBody netcoreapp3.1

  • unstable execution_time [-66.380ms; -40.971ms] or [-30.599%; -18.886%]
  • 🟩 throughput [+166311.558op/s; +224215.403op/s] or [+6.601%; +8.900%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeArgs net472

  • 🟥 execution_time [+301.597ms; +315.909ms] or [+150.698%; +157.849%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeArgs net6.0

  • unstable execution_time [+151.845ms; +191.243ms] or [+76.576%; +96.445%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeArgs netcoreapp3.1

  • unstable execution_time [+254.410ms; +289.981ms] or [+128.152%; +146.070%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeLegacyArgs net472

  • 🟥 execution_time [+298.296ms; +312.303ms] or [+146.511%; +153.391%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeLegacyArgs net6.0

  • 🟥 execution_time [+245.761ms; +261.210ms] or [+120.143%; +127.696%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeLegacyArgs netcoreapp3.1

  • 🟥 execution_time [+301.599ms; +307.413ms] or [+150.739%; +153.645%]

scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmarkWithAttack net6.0

  • 🟥 execution_time [+19.886µs; +43.547µs] or [+6.349%; +13.902%]
  • 🟥 throughput [-407.979op/s; -208.874op/s] or [-12.718%; -6.511%]

scenario:Benchmarks.Trace.AspNetCoreBenchmark.SendRequest net472

  • 🟥 execution_time [+300.042ms; +301.347ms] or [+149.752%; +150.403%]

scenario:Benchmarks.Trace.AspNetCoreBenchmark.SendRequest net6.0

  • unstable execution_time [+371.528ms; +395.328ms] or [+403.681%; +429.540%]
  • 🟥 throughput [-7117.708op/s; -6856.691op/s] or [-58.487%; -56.342%]

scenario:Benchmarks.Trace.AspNetCoreBenchmark.SendRequest netcoreapp3.1

  • unstable execution_time [+215.869ms; +277.567ms] or [+163.908%; +210.754%]
  • 🟥 throughput [-1463.102op/s; -1228.313op/s] or [-14.164%; -11.891%]

scenario:Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark.WriteAndFlushEnrichedTraces net472

  • 🟥 execution_time [+299.600ms; +316.946ms] or [+137.753%; +145.729%]
  • 🟥 throughput [-685.276op/s; -667.299op/s] or [-62.093%; -60.464%]

scenario:Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark.WriteAndFlushEnrichedTraces net6.0

  • unstable execution_time [-50.206ms; +83.654ms] or [-21.396%; +35.650%]
  • 🟥 throughput [-698.842op/s; -606.815op/s] or [-46.613%; -40.475%]

scenario:Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark.WriteAndFlushEnrichedTraces netcoreapp3.1

  • 🟥 allocated_mem [+2.305KB; +2.308KB] or [+5.442%; +5.450%]
  • 🟥 execution_time [+341.207ms; +349.916ms] or [+204.081%; +209.290%]
  • 🟥 throughput [-729.021op/s; -694.789op/s] or [-50.761%; -48.377%]

scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSliceWithPool net6.0

  • 🟩 execution_time [-72.052µs; -66.402µs] or [-6.682%; -6.158%]
  • 🟩 throughput [+61.101op/s; +66.205op/s] or [+6.588%; +7.138%]

scenario:Benchmarks.Trace.CharSliceBenchmark.OriginalCharSlice net6.0

  • 🟩 execution_time [-180.416µs; -165.409µs] or [-9.139%; -8.379%]
  • 🟩 throughput [+46.465op/s; +51.030op/s] or [+9.173%; +10.074%]

scenario:Benchmarks.Trace.CharSliceBenchmark.OriginalCharSlice netcoreapp3.1

  • 🟩 execution_time [-212.334µs; -199.518µs] or [-5.385%; -5.060%]
  • 🟩 throughput [+13.533op/s; +14.429op/s] or [+5.337%; +5.690%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearch net472

  • 🟥 execution_time [+304.850ms; +318.940ms] or [+153.517%; +160.612%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearch net6.0

  • 🟥 execution_time [+259.974ms; +276.141ms] or [+130.274%; +138.375%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearch netcoreapp3.1

  • 🟥 execution_time [+303.179ms; +310.355ms] or [+152.304%; +155.909%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearchAsync net472

  • 🟥 execution_time [+302.750ms; +316.669ms] or [+152.031%; +159.020%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearchAsync net6.0

  • unstable execution_time [+172.417ms; +219.938ms] or [+85.252%; +108.750%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearchAsync netcoreapp3.1

  • 🟥 execution_time [+302.597ms; +309.280ms] or [+153.369%; +156.757%]

scenario:Benchmarks.Trace.GraphQLBenchmark.ExecuteAsync net472

  • 🟥 execution_time [+305.053ms; +318.497ms] or [+153.109%; +159.857%]

scenario:Benchmarks.Trace.GraphQLBenchmark.ExecuteAsync net6.0

  • 🟥 execution_time [+303.220ms; +310.420ms] or [+151.127%; +154.716%]
  • 🟩 throughput [+46194.674op/s; +56315.889op/s] or [+9.173%; +11.183%]

scenario:Benchmarks.Trace.GraphQLBenchmark.ExecuteAsync netcoreapp3.1

  • 🟥 execution_time [+304.013ms; +310.156ms] or [+151.244%; +154.300%]

scenario:Benchmarks.Trace.ILoggerBenchmark.EnrichedLog net6.0

  • unstable execution_time [-90.325ms; -64.917ms] or [-42.002%; -30.187%]
  • unstable throughput [-99163.894op/s; -52361.106op/s] or [-27.203%; -14.364%]

scenario:Benchmarks.Trace.ILoggerBenchmark.EnrichedLog netcoreapp3.1

  • 🟩 execution_time [-97.363ms; -93.291ms] or [-48.839%; -46.796%]

scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatAspectBenchmark net6.0

  • 🟩 allocated_mem [-23.986KB; -23.963KB] or [-8.750%; -8.741%]
  • unstable execution_time [-15.817µs; +85.464µs] or [-3.126%; +16.892%]
  • unstable throughput [-174.333op/s; +116.609op/s] or [-8.699%; +5.819%]

scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatAspectBenchmark netcoreapp3.1

  • 🟩 execution_time [-97.928µs; -42.177µs] or [-16.970%; -7.309%]
  • 🟩 throughput [+154.355op/s; +308.597op/s] or [+8.818%; +17.631%]

scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatBenchmark net6.0

  • unstable execution_time [+3.129µs; +8.529µs] or [+7.397%; +20.160%]
  • 🟥 throughput [-3662.945op/s; -1548.795op/s] or [-15.420%; -6.520%]

scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatBenchmark netcoreapp3.1

  • unstable execution_time [-14.035µs; -4.447µs] or [-21.775%; -6.899%]
  • unstable throughput [+1431.503op/s; +3442.192op/s] or [+8.783%; +21.119%]

scenario:Benchmarks.Trace.Log4netBenchmark.EnrichedLog net472

  • 🟥 execution_time [+303.996ms; +318.147ms] or [+153.657%; +160.809%]

scenario:Benchmarks.Trace.Log4netBenchmark.EnrichedLog net6.0

  • unstable execution_time [+282.686ms; +302.457ms] or [+143.886%; +153.949%]

scenario:Benchmarks.Trace.Log4netBenchmark.EnrichedLog netcoreapp3.1

  • 🟥 execution_time [+301.472ms; +305.288ms] or [+150.924%; +152.834%]

scenario:Benchmarks.Trace.RedisBenchmark.SendReceive net6.0

  • unstable execution_time [-57.337ms; -28.298ms] or [-28.660%; -14.144%]
  • unstable throughput [-220842.625op/s; -150264.880op/s] or [-41.801%; -28.442%]

scenario:Benchmarks.Trace.RedisBenchmark.SendReceive netcoreapp3.1

  • unstable execution_time [-56.398ms; -26.277ms] or [-28.588%; -13.320%]

scenario:Benchmarks.Trace.SerilogBenchmark.EnrichedLog net472

  • 🟥 execution_time [+300.232ms; +312.910ms] or [+149.638%; +155.957%]

scenario:Benchmarks.Trace.SerilogBenchmark.EnrichedLog net6.0

  • unstable execution_time [+223.092ms; +264.821ms] or [+112.026%; +132.980%]

scenario:Benchmarks.Trace.SerilogBenchmark.EnrichedLog netcoreapp3.1

  • 🟥 execution_time [+303.438ms; +309.816ms] or [+153.884%; +157.119%]

scenario:Benchmarks.Trace.SingleSpanAspNetCoreBenchmark.SingleSpanAspNetCore net472

  • 🟥 execution_time [+299.606ms; +300.405ms] or [+149.445%; +149.844%]
  • unstable throughput [+44358528.978op/s; +58952396.601op/s] or [+32.305%; +42.933%]

scenario:Benchmarks.Trace.SingleSpanAspNetCoreBenchmark.SingleSpanAspNetCore net6.0

  • unstable execution_time [+371.949ms; +383.287ms] or [+462.585%; +476.685%]
  • 🟥 throughput [-7384.633op/s; -7191.071op/s] or [-57.087%; -55.591%]

scenario:Benchmarks.Trace.SingleSpanAspNetCoreBenchmark.SingleSpanAspNetCore netcoreapp3.1

  • 🟥 execution_time [+297.605ms; +300.663ms] or [+148.439%; +149.964%]
  • 🟥 throughput [-18534642.763op/s; -17024577.470op/s] or [-8.210%; -7.541%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishScope net6.0

  • unstable execution_time [-77.255ms; -43.854ms] or [-37.838%; -21.479%]
  • unstable throughput [-210572.623op/s; -46277.738op/s] or [-19.660%; -4.321%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishScope netcoreapp3.1

  • 🟩 execution_time [-99.729ms; -95.294ms] or [-50.463%; -48.219%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishSpan net6.0

  • unstable execution_time [-63.398ms; -37.062ms] or [-33.031%; -19.310%]
  • unstable throughput [-268132.473op/s; -86850.732op/s] or [-20.754%; -6.722%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishSpan netcoreapp3.1

  • unstable execution_time [-93.694ms; -71.840ms] or [-46.033%; -35.296%]
  • 🟩 throughput [+92819.984op/s; +100167.905op/s] or [+9.219%; +9.948%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishTwoScopes net6.0

  • unstable execution_time [-75.395ms; -50.417ms] or [-37.652%; -25.178%]
  • unstable throughput [-98867.753op/s; -20502.118op/s] or [-17.953%; -3.723%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishTwoScopes netcoreapp3.1

  • unstable execution_time [-88.847ms; -66.997ms] or [-44.640%; -33.662%]

scenario:Benchmarks.Trace.TraceAnnotationsBenchmark.RunOnMethodBegin net6.0

  • unstable execution_time [-76.664ms; -48.570ms] or [-38.345%; -24.294%]
  • unstable throughput [-237061.627op/s; -104709.139op/s] or [-26.486%; -11.699%]

scenario:Benchmarks.Trace.TraceAnnotationsBenchmark.RunOnMethodBegin netcoreapp3.1

  • unstable execution_time [-55.113ms; -27.067ms] or [-27.991%; -13.747%]

Known flaky benchmarks without significant changes:

  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_AddEvent_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_GetContext_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_GetContext_Sampled netcoreapp3.1
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_SetAttributes_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_SetStatus_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.ActivityBenchmark.StartSpan_UpdateName_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_AddEvent_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_AddEvent_Sampled netcoreapp3.1
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_GetContext_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_GetContext_Sampled netcoreapp3.1
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_RecordException_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_SetAttributes_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_SetStatus_Sampled net472
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_SetStatus_Sampled netcoreapp3.1
  • scenario:Benchmarks.OpenTelemetry.InstrumentedApi.Trace.TelemetrySpanBenchmark.StartSpan_UpdateName_Sampled net472
  • scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorMoreComplexBody net472
  • scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorSimpleBody net472
  • scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmark net472
  • scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmark net6.0
  • scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmark netcoreapp3.1
  • scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmarkWithAttack net472
  • scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmarkWithAttack netcoreapp3.1
  • scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSlice net472
  • scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSlice net6.0
  • scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSlice netcoreapp3.1
  • scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSliceWithPool net472
  • scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSliceWithPool netcoreapp3.1
  • scenario:Benchmarks.Trace.CharSliceBenchmark.OriginalCharSlice net472
  • scenario:Benchmarks.Trace.ILoggerBenchmark.EnrichedLog net472
  • scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatAspectBenchmark net472
  • scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatBenchmark net472
  • scenario:Benchmarks.Trace.RedisBenchmark.SendReceive net472
  • scenario:Benchmarks.Trace.SpanBenchmark.StartFinishScope net472
  • scenario:Benchmarks.Trace.SpanBenchmark.StartFinishSpan net472
  • scenario:Benchmarks.Trace.SpanBenchmark.StartFinishTwoScopes net472
  • scenario:Benchmarks.Trace.TraceAnnotationsBenchmark.RunOnMethodBegin net472

@dd-trace-dotnet-ci-bot

dd-trace-dotnet-ci-bot Bot commented Mar 19, 2026

Copy link
Copy Markdown

Execution-Time Benchmarks Report ⏱️

Execution-time results for samples comparing This PR (8338) and master.

✅ No regressions detected - check the details below

Full Metrics Comparison

FakeDbCommand

Metric Master (Mean ± 95% CI) Current (Mean ± 95% CI) Change Status
.NET Framework 4.8 - Baseline
duration75.28 ± (74.97 - 75.58) ms74.45 ± (74.58 - 75.29) ms-1.1%
.NET Framework 4.8 - Bailout
duration78.09 ± (78.15 - 78.79) ms78.72 ± (78.70 - 79.15) ms+0.8%✅⬆️
.NET Framework 4.8 - CallTarget+Inlining+NGEN
duration1120.81 ± (1121.34 - 1128.97) ms1128.18 ± (1128.89 - 1137.55) ms+0.7%✅⬆️
.NET Core 3.1 - Baseline
process.internal_duration_ms22.60 ± (22.54 - 22.66) ms22.67 ± (22.62 - 22.72) ms+0.3%✅⬆️
process.time_to_main_ms85.61 ± (85.29 - 85.94) ms85.93 ± (85.67 - 86.20) ms+0.4%✅⬆️
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed10.91 ± (10.91 - 10.92) MB10.92 ± (10.91 - 10.92) MB+0.1%✅⬆️
runtime.dotnet.threads.count12 ± (12 - 12)12 ± (12 - 12)+0.0%
.NET Core 3.1 - Bailout
process.internal_duration_ms22.41 ± (22.36 - 22.45) ms22.47 ± (22.43 - 22.51) ms+0.3%✅⬆️
process.time_to_main_ms86.03 ± (85.84 - 86.23) ms85.73 ± (85.51 - 85.95) ms-0.4%
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed10.90 ± (10.89 - 10.90) MB10.95 ± (10.94 - 10.95) MB+0.5%✅⬆️
runtime.dotnet.threads.count13 ± (13 - 13)13 ± (13 - 13)+0.0%
.NET Core 3.1 - CallTarget+Inlining+NGEN
process.internal_duration_ms205.14 ± (204.60 - 205.69) ms205.91 ± (205.36 - 206.46) ms+0.4%✅⬆️
process.time_to_main_ms567.03 ± (565.45 - 568.61) ms566.81 ± (565.48 - 568.13) ms-0.0%
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed49.86 ± (49.83 - 49.88) MB49.77 ± (49.74 - 49.80) MB-0.2%
runtime.dotnet.threads.count28 ± (28 - 28)28 ± (28 - 28)-0.0%
.NET 6 - Baseline
process.internal_duration_ms21.45 ± (21.39 - 21.50) ms21.70 ± (21.63 - 21.76) ms+1.2%✅⬆️
process.time_to_main_ms75.39 ± (75.05 - 75.72) ms76.40 ± (76.10 - 76.70) ms+1.3%✅⬆️
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed10.61 ± (10.61 - 10.61) MB10.63 ± (10.63 - 10.63) MB+0.2%✅⬆️
runtime.dotnet.threads.count10 ± (10 - 10)10 ± (10 - 10)+0.0%
.NET 6 - Bailout
process.internal_duration_ms21.39 ± (21.34 - 21.45) ms21.35 ± (21.31 - 21.39) ms-0.2%
process.time_to_main_ms76.36 ± (76.12 - 76.60) ms75.57 ± (75.37 - 75.77) ms-1.0%
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed10.73 ± (10.73 - 10.74) MB10.75 ± (10.75 - 10.75) MB+0.1%✅⬆️
runtime.dotnet.threads.count11 ± (11 - 11)11 ± (11 - 11)+0.0%
.NET 6 - CallTarget+Inlining+NGEN
process.internal_duration_ms352.66 ± (350.79 - 354.52) ms352.25 ± (350.29 - 354.20) ms-0.1%
process.time_to_main_ms564.21 ± (562.60 - 565.81) ms563.93 ± (562.46 - 565.40) ms-0.0%
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed50.99 ± (50.97 - 51.02) MB51.13 ± (51.11 - 51.15) MB+0.3%✅⬆️
runtime.dotnet.threads.count28 ± (28 - 28)28 ± (28 - 28)-0.5%
.NET 8 - Baseline
process.internal_duration_ms19.43 ± (19.40 - 19.47) ms19.40 ± (19.35 - 19.44) ms-0.2%
process.time_to_main_ms72.68 ± (72.53 - 72.83) ms73.04 ± (72.84 - 73.24) ms+0.5%✅⬆️
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed7.67 ± (7.66 - 7.67) MB7.67 ± (7.67 - 7.68) MB+0.1%✅⬆️
runtime.dotnet.threads.count10 ± (10 - 10)10 ± (10 - 10)+0.0%
.NET 8 - Bailout
process.internal_duration_ms19.86 ± (19.81 - 19.92) ms19.68 ± (19.62 - 19.73) ms-0.9%
process.time_to_main_ms76.49 ± (76.21 - 76.77) ms75.99 ± (75.74 - 76.25) ms-0.6%
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed7.71 ± (7.71 - 7.72) MB7.71 ± (7.70 - 7.71) MB-0.1%
runtime.dotnet.threads.count11 ± (11 - 11)11 ± (11 - 11)+0.0%
.NET 8 - CallTarget+Inlining+NGEN
process.internal_duration_ms286.09 ± (282.45 - 289.73) ms278.97 ± (276.70 - 281.24) ms-2.5%
process.time_to_main_ms519.87 ± (518.61 - 521.12) ms518.98 ± (517.58 - 520.37) ms-0.2%
runtime.dotnet.exceptions.count0 ± (0 - 0)0 ± (0 - 0)+0.0%
runtime.dotnet.mem.committed37.94 ± (37.91 - 37.97) MB37.84 ± (37.81 - 37.87) MB-0.3%
runtime.dotnet.threads.count27 ± (27 - 27)27 ± (27 - 27)-0.2%

HttpMessageHandler

Metric Master (Mean ± 95% CI) Current (Mean ± 95% CI) Change Status
.NET Framework 4.8 - Baseline
duration194.53 ± (194.44 - 195.16) ms195.14 ± (194.79 - 195.76) ms+0.3%✅⬆️
.NET Framework 4.8 - Bailout
duration198.45 ± (198.25 - 198.78) ms197.63 ± (197.37 - 197.94) ms-0.4%
.NET Framework 4.8 - CallTarget+Inlining+NGEN
duration1210.00 ± (1209.50 - 1215.00) ms1206.12 ± (1206.51 - 1214.26) ms-0.3%
.NET Core 3.1 - Baseline
process.internal_duration_ms187.17 ± (186.78 - 187.56) ms189.09 ± (188.69 - 189.49) ms+1.0%✅⬆️
process.time_to_main_ms81.27 ± (81.09 - 81.46) ms82.12 ± (81.92 - 82.32) ms+1.0%✅⬆️
runtime.dotnet.exceptions.count3 ± (3 - 3)3 ± (3 - 3)+0.0%
runtime.dotnet.mem.committed16.05 ± (16.04 - 16.07) MB16.09 ± (16.06 - 16.11) MB+0.2%✅⬆️
runtime.dotnet.threads.count20 ± (19 - 20)20 ± (20 - 20)+0.6%✅⬆️
.NET Core 3.1 - Bailout
process.internal_duration_ms186.80 ± (186.51 - 187.09) ms188.81 ± (188.50 - 189.11) ms+1.1%✅⬆️
process.time_to_main_ms82.92 ± (82.77 - 83.07) ms83.52 ± (83.37 - 83.68) ms+0.7%✅⬆️
runtime.dotnet.exceptions.count3 ± (3 - 3)3 ± (3 - 3)+0.0%
runtime.dotnet.mem.committed16.20 ± (16.17 - 16.24) MB16.16 ± (16.13 - 16.19) MB-0.3%
runtime.dotnet.threads.count21 ± (21 - 21)21 ± (20 - 21)-0.6%
.NET Core 3.1 - CallTarget+Inlining+NGEN
process.internal_duration_ms373.76 ± (372.69 - 374.82) ms369.58 ± (368.27 - 370.88) ms-1.1%
process.time_to_main_ms551.42 ± (550.08 - 552.76) ms548.45 ± (547.10 - 549.80) ms-0.5%
runtime.dotnet.exceptions.count3 ± (3 - 3)3 ± (3 - 3)+0.0%
runtime.dotnet.mem.committed58.46 ± (58.42 - 58.50) MB58.48 ± (58.43 - 58.52) MB+0.0%✅⬆️
runtime.dotnet.threads.count30 ± (30 - 30)30 ± (30 - 30)+0.1%✅⬆️
.NET 6 - Baseline
process.internal_duration_ms195.73 ± (195.16 - 196.31) ms193.73 ± (193.17 - 194.29) ms-1.0%
process.time_to_main_ms72.01 ± (71.78 - 72.23) ms71.71 ± (71.47 - 71.96) ms-0.4%
runtime.dotnet.exceptions.count4 ± (4 - 4)4 ± (4 - 4)+0.0%
runtime.dotnet.mem.committed16.34 ± (16.33 - 16.36) MB16.33 ± (16.28 - 16.37) MB-0.1%
runtime.dotnet.threads.count19 ± (19 - 19)19 ± (19 - 19)-0.9%
.NET 6 - Bailout
process.internal_duration_ms193.06 ± (192.74 - 193.38) ms192.72 ± (192.32 - 193.11) ms-0.2%
process.time_to_main_ms72.03 ± (71.89 - 72.18) ms72.37 ± (72.20 - 72.54) ms+0.5%✅⬆️
runtime.dotnet.exceptions.count4 ± (4 - 4)4 ± (4 - 4)+0.0%
runtime.dotnet.mem.committed16.30 ± (16.21 - 16.39) MB16.46 ± (16.44 - 16.48) MB+1.0%✅⬆️
runtime.dotnet.threads.count20 ± (20 - 20)20 ± (20 - 20)+1.6%✅⬆️
.NET 6 - CallTarget+Inlining+NGEN
process.internal_duration_ms568.22 ± (565.17 - 571.26) ms573.22 ± (570.40 - 576.05) ms+0.9%✅⬆️
process.time_to_main_ms543.51 ± (542.52 - 544.51) ms544.46 ± (543.17 - 545.75) ms+0.2%✅⬆️
runtime.dotnet.exceptions.count4 ± (4 - 4)4 ± (4 - 4)+0.0%
runtime.dotnet.mem.committed61.93 ± (61.90 - 61.96) MB61.95 ± (61.92 - 61.99) MB+0.0%✅⬆️
runtime.dotnet.threads.count31 ± (31 - 31)31 ± (31 - 31)-0.7%
.NET 8 - Baseline
process.internal_duration_ms194.85 ± (194.35 - 195.36) ms196.41 ± (195.94 - 196.87) ms+0.8%✅⬆️
process.time_to_main_ms71.77 ± (71.59 - 71.95) ms72.65 ± (72.46 - 72.83) ms+1.2%✅⬆️
runtime.dotnet.exceptions.count4 ± (4 - 4)4 ± (4 - 4)+0.0%
runtime.dotnet.mem.committed11.73 ± (11.72 - 11.75) MB11.70 ± (11.68 - 11.71) MB-0.3%
runtime.dotnet.threads.count18 ± (18 - 18)18 ± (18 - 18)+0.0%✅⬆️
.NET 8 - Bailout
process.internal_duration_ms193.07 ± (192.55 - 193.59) ms190.81 ± (190.48 - 191.15) ms-1.2%
process.time_to_main_ms72.44 ± (72.25 - 72.62) ms71.90 ± (71.74 - 72.06) ms-0.7%
runtime.dotnet.exceptions.count4 ± (4 - 4)4 ± (4 - 4)+0.0%
runtime.dotnet.mem.committed11.80 ± (11.78 - 11.81) MB11.81 ± (11.78 - 11.84) MB+0.1%✅⬆️
runtime.dotnet.threads.count19 ± (19 - 19)19 ± (19 - 19)+0.1%✅⬆️
.NET 8 - CallTarget+Inlining+NGEN
process.internal_duration_ms491.26 ± (488.81 - 493.72) ms493.73 ± (491.44 - 496.02) ms+0.5%✅⬆️
process.time_to_main_ms497.98 ± (497.09 - 498.88) ms502.14 ± (501.14 - 503.15) ms+0.8%✅⬆️
runtime.dotnet.exceptions.count4 ± (4 - 4)4 ± (4 - 4)+0.0%
runtime.dotnet.mem.committed51.62 ± (51.59 - 51.64) MB51.57 ± (51.54 - 51.60) MB-0.1%
runtime.dotnet.threads.count29 ± (29 - 29)29 ± (29 - 29)-0.2%
Comparison explanation

Execution-time benchmarks measure the whole time it takes to execute a program, and are intended to measure the one-off costs. Cases where the execution time results for the PR are worse than latest master results are highlighted in **red**. The following thresholds were used for comparing the execution times:

  • Welch test with statistical test for significance of 5%
  • Only results indicating a difference greater than 5% and 5 ms are considered.

Note that these results are based on a single point-in-time result for each branch. For full results, see the dashboard.

Graphs show the p99 interval based on the mean and StdDev of the test run, as well as the mean value of the run (shown as a diamond below the graph).

Duration charts
FakeDbCommand (.NET Framework 4.8)
gantt
    title Execution time (ms) FakeDbCommand (.NET Framework 4.8)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (75ms)  : 69, 80
    master - mean (75ms)  : 71, 80

    section Bailout
    This PR (8338) - mean (79ms)  : 76, 82
    master - mean (78ms)  : 75, 82

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,133ms)  : 1069, 1198
    master - mean (1,125ms)  : 1071, 1179

Loading
FakeDbCommand (.NET Core 3.1)
gantt
    title Execution time (ms) FakeDbCommand (.NET Core 3.1)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (115ms)  : 111, 120
    master - mean (115ms)  : 108, 123

    section Bailout
    This PR (8338) - mean (115ms)  : 112, 118
    master - mean (115ms)  : 112, 118

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (811ms)  : 782, 839
    master - mean (808ms)  : 783, 834

Loading
FakeDbCommand (.NET 6)
gantt
    title Execution time (ms) FakeDbCommand (.NET 6)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (105ms)  : 99, 111
    master - mean (103ms)  : 98, 109

    section Bailout
    This PR (8338) - mean (103ms)  : 99, 108
    master - mean (104ms)  : 99, 109

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (947ms)  : 915, 979
    master - mean (946ms)  : 910, 981

Loading
FakeDbCommand (.NET 8)
gantt
    title Execution time (ms) FakeDbCommand (.NET 8)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (100ms)  : 96, 104
    master - mean (100ms)  : 96, 104

    section Bailout
    This PR (8338) - mean (104ms)  : 99, 108
    master - mean (104ms)  : 99, 110

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (828ms)  : 785, 871
    master - mean (835ms)  : 778, 892

Loading
HttpMessageHandler (.NET Framework 4.8)
gantt
    title Execution time (ms) HttpMessageHandler (.NET Framework 4.8)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (195ms)  : 190, 200
    master - mean (195ms)  : 191, 198

    section Bailout
    This PR (8338) - mean (198ms)  : 195, 200
    master - mean (199ms)  : 196, 201

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,210ms)  : 1154, 1267
    master - mean (1,212ms)  : 1173, 1251

Loading
HttpMessageHandler (.NET Core 3.1)
gantt
    title Execution time (ms) HttpMessageHandler (.NET Core 3.1)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (280ms)  : 275, 285
    master - mean (277ms)  : 269, 284

    section Bailout
    This PR (8338) - mean (281ms)  : 277, 285
    master - mean (278ms)  : 274, 282

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (957ms)  : 937, 977
    master - mean (964ms)  : 938, 990

Loading
HttpMessageHandler (.NET 6)
gantt
    title Execution time (ms) HttpMessageHandler (.NET 6)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (274ms)  : 261, 288
    master - mean (276ms)  : 263, 290

    section Bailout
    This PR (8338) - mean (273ms)  : 265, 282
    master - mean (273ms)  : 268, 278

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,147ms)  : 1108, 1185
    master - mean (1,144ms)  : 1097, 1191

Loading
HttpMessageHandler (.NET 8)
gantt
    title Execution time (ms) HttpMessageHandler (.NET 8)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (279ms)  : 269, 289
    master - mean (277ms)  : 266, 287

    section Bailout
    This PR (8338) - mean (272ms)  : 268, 277
    master - mean (275ms)  : 264, 287

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,028ms)  : 985, 1072
    master - mean (1,023ms)  : 980, 1067

Loading

@gleocadie
gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch 9 times, most recently from ba7a85e to c4d42ed Compare March 24, 2026 16:53
@gleocadie
gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch 10 times, most recently from 876012b to 774f6b9 Compare March 30, 2026 23:24
@gleocadie
gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch 6 times, most recently from f3d5056 to 4350315 Compare April 10, 2026 10:57
@gleocadie
gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch from 4350315 to 3e6ce93 Compare April 10, 2026 12:36
gleocadie and others added 26 commits May 11, 2026 07:59
…m64)

UnwindTracersProvider::ScopedTracer has a user-declared destructor that
pushes its TracerNode back onto the free-list. It had no explicit move
ops, which meant the compiler kept the implicit (deprecated) copy-assign
and omitted the implicit move. TimerCreateCpuProfiler::Collect() uses
assignment on every arm64 CPU sample when debug logging is on, so the
temporary and the local both ended up releasing the same node, corrupting
the free-list.

- Delete the copy ctor/assignment and define explicit move ctor/assignment
  that null out the source's _provider/_node.
- Default-initialize _provider/_node in the class body so the
  ScopedTracer(nullptr) overload no longer leaves _node indeterminate.

Made-with: Cursor
…ines)

- [F3] Rewrite the .NET<5 arm64 Log::Warn in CorProfilerCallback::Initialize
  to use "Continuous Profiler" and "arm64 Linux" per AGENTS.md guidelines.
- [B4] Expand the no_sanitize("vptr") rationale above the first call-site
  to explicitly cover the three clang+arm64 suppression points below.
- [F4] Document that TimerCreateCpuProfiler::_useUnwinderTracer is a
  one-shot snapshot of Log::IsDebugEnabled() captured at construction.
- [F5] Collapse the duplicated AddModuleRangesToCache declaration in
  ManagedCodeCache.h by toggling visibility with a single #ifdef DD_TEST
  public: / #else private: / #endif block.
- [F6] Fix the "GetfunctionId" typo and clarify the comment around the
  defensive !isR2r.has_value() guard.
- [F7] Drop the stray blank line introduced in LinuxStackFramesCollector
  after RegisterHandler.
- [F8] Default-initialize StackFramesCollectorBase::_tracer{nullptr} to
  remove any future indeterminate-value hazard.
- [C4] Append a trailing newline to Backtrace2Unwinder.h, HybridUnwinder.h,
  IUnwinder.h, LinuxStackFramesCollector.h, TimerCreateCpuProfiler.h.

Made-with: Cursor
- [C7] Explain in profiler/src/Demos/Directory.Build.props why
  netcoreapp3.1 is excluded on arm64 Linux (the Continuous Profiler
  refuses to initialize on .NET Core 3.1 / arm64).
- [E1] Clarify in PublishProfilerLinux that the linux-arm64 and
  linux-musl-arm64 RID folders are both populated, via the glibc and
  Alpine/musl CI legs respectively.
- [E2] Add a TODO + tracking-issue placeholder next to the
  TSAN-disabled-on-arm64 conditions (48-bit VMA requirement on CI hosts).
- [E3] Document why we preload libasan.so.5 on arm64 (older gcc 9 image)
  vs libasan.so.6 on x64.
- [E4] Describe in build/cmake/FindLibunwind.cmake the patches carried
  by DataDog/libunwind@gleocadie/v1.8.1-custom-3 and why we can't move
  to upstream v1.8.3 yet.

Made-with: Cursor
…opt cases [D1]

Regression guards for two behaviors that previously caused the arm64
exception profiler to surface a long tail of NotResolvedFrame entries:

- Fake IPs (FakeUnknownIP / FakeLockContentionIP / FakeAllocationIP)
  short-circuit to {isResolved=true, <corresponding placeholder>} without
  calling ICorProfilerInfo::GetFunctionFromIP.
- On Windows, if the cached GetFunctionFromIP path throws an SEH
  exception (simulated), FrameStore::GetFrame translates the resulting
  std::nullopt from ManagedCodeCache into {isResolved=true, NotResolvedFrame}
  so the legacy placeholder behavior is preserved.

Made-with: Cursor
@gleocadie
gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch from 16e8dde to 3d2d5b9 Compare May 11, 2026 07:59

@r1viollet r1viollet left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, a big one! 👏

@gleocadie
gleocadie merged commit d63034b into master May 15, 2026
143 of 147 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area:profiler Issues related to the continous-profiler type:new-feature

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants