[Profiler] Add support for ARM64 by gleocadie · Pull Request #8338 · DataDog/dd-trace-dotnet

gleocadie · 2026-03-19T10:16:16Z

Summary of changes

Reason for change

Implementation details

Test coverage

Other details

pr-commenter · 2026-03-19T11:00:15Z

Benchmarks

Benchmark execution time: 2026-03-31 00:07:59

Comparing candidate commit 774f6b9 in PR branch gleocadie/add-frame-based-pointer-unwinding-for-arm64 with baseline commit f22a608 in branch master.

Found 8 performance improvements and 10 performance regressions! Performance is the same for 251 metrics, 19 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:Benchmarks.Trace.ActivityBenchmark.StartStopWithChild netcoreapp3.1

🟩 execution_time [-20.646ms; -18.887ms] or [-10.221%; -9.350%]

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

🟩 execution_time [-99.736ms; -99.594ms] or [-48.669%; -48.599%]

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

🟩 execution_time [-87.336ms; -87.205ms] or [-43.700%; -43.635%]

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

🟥 execution_time [+16.376ms; +22.408ms] or [+8.457%; +11.572%]

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

🟩 execution_time [-24.406ms; -18.690ms] or [-11.080%; -8.485%]

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

🟩 execution_time [-85.868µs; -80.905µs] or [-5.910%; -5.568%]
🟩 throughput [+40.628op/s; +43.192op/s] or [+5.903%; +6.275%]

scenario:Benchmarks.Trace.CharSliceBenchmark.OriginalCharSlice net472

🟩 execution_time [-165.526µs; -160.528µs] or [-6.029%; -5.847%]
🟩 throughput [+22.628op/s; +23.357op/s] or [+6.213%; +6.413%]

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

🟥 throughput [-41340.105op/s; -32118.558op/s] or [-6.593%; -5.122%]

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

🟥 throughput [-18740.230op/s; -17556.188op/s] or [-12.038%; -11.277%]

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

🟥 execution_time [+102.665ms; +104.987ms] or [+107.274%; +109.699%]

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

🟥 throughput [-150617.175op/s; -140576.830op/s] or [-28.508%; -26.608%]

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

🟥 execution_time [+11.499ms; +16.821ms] or [+5.835%; +8.535%]

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

🟥 throughput [-40895.107op/s; -38174.423op/s] or [-18.010%; -16.812%]

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

🟥 execution_time [+20.656ms; +24.267ms] or [+10.520%; +12.359%]

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

🟥 execution_time [+14.057ms; +14.895ms] or [+7.098%; +7.521%]

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

🟥 execution_time [+10.234ms; +14.781ms] or [+5.159%; +7.452%]

dd-trace-dotnet-ci-bot · 2026-03-19T11:07:18Z

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
duration	71.99 ± (72.07 - 72.44) ms	72.01 ± (71.97 - 72.23) ms	+0.0%	✅⬆️
.NET Framework 4.8 - Bailout
duration	75.66 ± (75.57 - 75.92) ms	76.37 ± (76.26 - 76.62) ms	+0.9%	✅⬆️
.NET Framework 4.8 - CallTarget+Inlining+NGEN
duration	1069.02 ± (1069.60 - 1075.40) ms	1072.44 ± (1073.29 - 1078.59) ms	+0.3%	✅⬆️
.NET Core 3.1 - Baseline
process.internal_duration_ms	22.54 ± (22.46 - 22.63) ms	22.07 ± (22.03 - 22.11) ms	-2.1%	✅
process.time_to_main_ms	84.75 ± (84.24 - 85.26) ms	82.86 ± (82.67 - 83.05) ms	-2.2%	✅
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	10.91 ± (10.90 - 10.91) MB	10.91 ± (10.91 - 10.92) MB	+0.1%	✅⬆️
runtime.dotnet.threads.count	12 ± (12 - 12)	12 ± (12 - 12)	+0.0%	✅
.NET Core 3.1 - Bailout
process.internal_duration_ms	22.25 ± (22.22 - 22.28) ms	22.13 ± (22.09 - 22.16) ms	-0.6%	✅
process.time_to_main_ms	84.75 ± (84.56 - 84.94) ms	84.51 ± (84.32 - 84.70) ms	-0.3%	✅
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	10.95 ± (10.95 - 10.95) MB	10.94 ± (10.94 - 10.95) MB	-0.1%	✅
runtime.dotnet.threads.count	13 ± (13 - 13)	13 ± (13 - 13)	+0.0%	✅
.NET Core 3.1 - CallTarget+Inlining+NGEN
process.internal_duration_ms	222.65 ± (221.58 - 223.72) ms	222.98 ± (221.77 - 224.20) ms	+0.2%	✅⬆️
process.time_to_main_ms	534.07 ± (533.06 - 535.08) ms	533.68 ± (532.53 - 534.83) ms	-0.1%	✅
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	48.27 ± (48.24 - 48.30) MB	48.26 ± (48.23 - 48.29) MB	-0.0%	✅
runtime.dotnet.threads.count	28 ± (28 - 28)	28 ± (28 - 28)	-0.2%	✅
.NET 6 - Baseline
process.internal_duration_ms	20.86 ± (20.83 - 20.90) ms	20.91 ± (20.88 - 20.94) ms	+0.2%	✅⬆️
process.time_to_main_ms	71.58 ± (71.42 - 71.74) ms	71.96 ± (71.79 - 72.13) ms	+0.5%	✅⬆️
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	10.61 ± (10.61 - 10.61) MB	10.63 ± (10.63 - 10.63) MB	+0.2%	✅⬆️
runtime.dotnet.threads.count	10 ± (10 - 10)	10 ± (10 - 10)	+0.0%	✅
.NET 6 - Bailout
process.internal_duration_ms	21.07 ± (21.04 - 21.10) ms	20.74 ± (20.70 - 20.78) ms	-1.6%	✅
process.time_to_main_ms	73.17 ± (73.01 - 73.34) ms	72.69 ± (72.53 - 72.86) ms	-0.7%	✅
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	10.71 ± (10.71 - 10.72) MB	10.74 ± (10.74 - 10.75) MB	+0.3%	✅⬆️
runtime.dotnet.threads.count	11 ± (11 - 11)	11 ± (11 - 11)	+0.0%	✅
.NET 6 - CallTarget+Inlining+NGEN
process.internal_duration_ms	390.50 ± (388.33 - 392.66) ms	385.73 ± (383.25 - 388.20) ms	-1.2%	✅
process.time_to_main_ms	530.09 ± (529.12 - 531.06) ms	532.41 ± (531.48 - 533.33) ms	+0.4%	✅⬆️
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	50.30 ± (50.27 - 50.32) MB	50.32 ± (50.30 - 50.35) MB	+0.0%	✅⬆️
runtime.dotnet.threads.count	28 ± (28 - 28)	28 ± (28 - 28)	+0.1%	✅⬆️
.NET 8 - Baseline
process.internal_duration_ms	19.24 ± (19.21 - 19.28) ms	19.30 ± (19.26 - 19.33) ms	+0.3%	✅⬆️
process.time_to_main_ms	71.98 ± (71.82 - 72.15) ms	71.95 ± (71.78 - 72.11) ms	-0.0%	✅
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	7.66 ± (7.66 - 7.67) MB	7.68 ± (7.67 - 7.68) MB	+0.2%	✅⬆️
runtime.dotnet.threads.count	10 ± (10 - 10)	10 ± (10 - 10)	+0.0%	✅
.NET 8 - Bailout
process.internal_duration_ms	19.38 ± (19.34 - 19.43) ms	19.27 ± (19.22 - 19.32) ms	-0.6%	✅
process.time_to_main_ms	73.10 ± (72.95 - 73.24) ms	72.80 ± (72.63 - 72.98) ms	-0.4%	✅
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	7.70 ± (7.69 - 7.71) MB	7.74 ± (7.73 - 7.75) MB	+0.5%	✅⬆️
runtime.dotnet.threads.count	11 ± (11 - 11)	11 ± (11 - 11)	+0.0%	✅
.NET 8 - CallTarget+Inlining+NGEN
process.internal_duration_ms	309.95 ± (307.65 - 312.24) ms	309.04 ± (306.77 - 311.31) ms	-0.3%	✅
process.time_to_main_ms	488.91 ± (488.14 - 489.68) ms	491.42 ± (490.59 - 492.24) ms	+0.5%	✅⬆️
runtime.dotnet.exceptions.count	0 ± (0 - 0)	0 ± (0 - 0)	+0.0%	✅
runtime.dotnet.mem.committed	37.21 ± (37.18 - 37.23) MB	37.22 ± (37.20 - 37.24) MB	+0.0%	✅⬆️
runtime.dotnet.threads.count	27 ± (27 - 27)	27 ± (27 - 27)	+0.0%	✅⬆️

HttpMessageHandler

Metric	Master (Mean ± 95% CI)	Current (Mean ± 95% CI)	Change	Status
.NET Framework 4.8 - Baseline
duration	212.28 ± (212.00 - 212.96) ms	204.75 ± (204.93 - 206.04) ms	-3.5%	✅
.NET Framework 4.8 - Bailout
duration	216.60 ± (216.22 - 217.27) ms	210.01 ± (209.51 - 210.56) ms	-3.0%	✅
.NET Framework 4.8 - CallTarget+Inlining+NGEN
duration	1248.66 ± (1245.83 - 1253.25) ms	1200.30 ± (1200.04 - 1207.65) ms	-3.9%	✅
.NET Core 3.1 - Baseline
process.internal_duration_ms	208.15 ± (207.68 - 208.62) ms	200.42 ± (199.97 - 200.87) ms	-3.7%	✅
process.time_to_main_ms	90.85 ± (90.55 - 91.15) ms	86.63 ± (86.30 - 86.96) ms	-4.6%	✅
runtime.dotnet.exceptions.count	3 ± (3 - 3)	3 ± (3 - 3)	+0.0%	✅
runtime.dotnet.mem.committed	15.94 ± (15.92 - 15.95) MB	15.98 ± (15.96 - 16.01) MB	+0.3%	✅⬆️
runtime.dotnet.threads.count	20 ± (20 - 20)	20 ± (20 - 20)	-0.6%	✅
.NET Core 3.1 - Bailout
process.internal_duration_ms	209.42 ± (208.87 - 209.96) ms	199.69 ± (199.25 - 200.14) ms	-4.6%	✅
process.time_to_main_ms	92.71 ± (92.42 - 93.00) ms	88.06 ± (87.79 - 88.33) ms	-5.0%	✅
runtime.dotnet.exceptions.count	3 ± (3 - 3)	3 ± (3 - 3)	+0.0%	✅
runtime.dotnet.mem.committed	15.99 ± (15.97 - 16.01) MB	16.15 ± (16.12 - 16.17) MB	+1.0%	✅⬆️
runtime.dotnet.threads.count	21 ± (21 - 21)	21 ± (21 - 21)	-0.9%	✅
.NET Core 3.1 - CallTarget+Inlining+NGEN
process.internal_duration_ms	418.97 ± (417.11 - 420.82) ms	407.20 ± (405.55 - 408.84) ms	-2.8%	✅
process.time_to_main_ms	567.14 ± (565.72 - 568.57) ms	549.51 ± (548.17 - 550.85) ms	-3.1%	✅
runtime.dotnet.exceptions.count	3 ± (3 - 3)	3 ± (3 - 3)	+0.0%	✅
runtime.dotnet.mem.committed	59.08 ± (59.02 - 59.13) MB	59.20 ± (59.13 - 59.26) MB	+0.2%	✅⬆️
runtime.dotnet.threads.count	30 ± (30 - 30)	30 ± (30 - 30)	-0.2%	✅
.NET 6 - Baseline
process.internal_duration_ms	213.13 ± (212.66 - 213.61) ms	204.88 ± (204.45 - 205.31) ms	-3.9%	✅
process.time_to_main_ms	78.73 ± (78.47 - 78.99) ms	75.15 ± (74.92 - 75.39) ms	-4.5%	✅
runtime.dotnet.exceptions.count	4 ± (4 - 4)	4 ± (4 - 4)	+0.0%	✅
runtime.dotnet.mem.committed	16.23 ± (16.22 - 16.25) MB	16.28 ± (16.26 - 16.30) MB	+0.3%	✅⬆️
runtime.dotnet.threads.count	20 ± (19 - 20)	19 ± (19 - 20)	-0.2%	✅
.NET 6 - Bailout
process.internal_duration_ms	213.11 ± (212.53 - 213.69) ms	202.86 ± (202.44 - 203.29) ms	-4.8%	✅
process.time_to_main_ms	80.34 ± (80.12 - 80.57) ms	75.63 ± (75.39 - 75.87) ms	-5.9%	✅
runtime.dotnet.exceptions.count	4 ± (4 - 4)	4 ± (4 - 4)	+0.0%	✅
runtime.dotnet.mem.committed	16.23 ± (16.21 - 16.26) MB	16.34 ± (16.31 - 16.37) MB	+0.6%	✅⬆️
runtime.dotnet.threads.count	21 ± (20 - 21)	20 ± (20 - 21)	-0.5%	✅
.NET 6 - CallTarget+Inlining+NGEN
process.internal_duration_ms	597.39 ± (595.21 - 599.57) ms	596.49 ± (593.63 - 599.36) ms	-0.2%	✅
process.time_to_main_ms	571.09 ± (569.78 - 572.40) ms	519.19 ± (518.04 - 520.34) ms	-9.1%	✅
runtime.dotnet.exceptions.count	4 ± (4 - 4)	4 ± (4 - 4)	+0.0%	✅
runtime.dotnet.mem.committed	61.71 ± (61.60 - 61.82) MB	61.86 ± (61.76 - 61.96) MB	+0.2%	✅⬆️
runtime.dotnet.threads.count	31 ± (31 - 31)	30 ± (30 - 30)	-1.7%	✅
.NET 8 - Baseline
process.internal_duration_ms	211.64 ± (211.21 - 212.07) ms	185.90 ± (185.67 - 186.12) ms	-12.2%	✅
process.time_to_main_ms	78.83 ± (78.53 - 79.13) ms	68.23 ± (68.13 - 68.33) ms	-13.4%	✅
runtime.dotnet.exceptions.count	4 ± (4 - 4)	4 ± (4 - 4)	+0.0%	✅
runtime.dotnet.mem.committed	11.54 ± (11.52 - 11.56) MB	11.78 ± (11.71 - 11.85) MB	+2.0%	✅⬆️
runtime.dotnet.threads.count	19 ± (19 - 19)	18 ± (17 - 18)	-7.2%	✅
.NET 8 - Bailout
process.internal_duration_ms	211.89 ± (211.40 - 212.37) ms	185.58 ± (185.43 - 185.73) ms	-12.4%	✅
process.time_to_main_ms	79.80 ± (79.56 - 80.04) ms	69.32 ± (69.26 - 69.38) ms	-13.1%	✅
runtime.dotnet.exceptions.count	4 ± (4 - 4)	4 ± (4 - 4)	+0.0%	✅
runtime.dotnet.mem.committed	11.62 ± (11.60 - 11.64) MB	11.55 ± (11.45 - 11.66) MB	-0.6%	✅
runtime.dotnet.threads.count	20 ± (20 - 20)	18 ± (18 - 19)	-7.8%	✅
.NET 8 - CallTarget+Inlining+NGEN
process.internal_duration_ms	570.41 ± (562.32 - 578.51) ms	518.30 ± (515.17 - 521.43) ms	-9.1%	✅
process.time_to_main_ms	524.72 ± (523.63 - 525.82) ms	473.73 ± (473.00 - 474.45) ms	-9.7%	✅
runtime.dotnet.exceptions.count	4 ± (4 - 4)	4 ± (4 - 4)	+0.0%	✅
runtime.dotnet.mem.committed	51.39 ± (51.29 - 51.48) MB	51.06 ± (51.03 - 51.08) MB	-0.6%	✅
runtime.dotnet.threads.count	30 ± (30 - 30)	30 ± (30 - 30)	-0.3%	✅

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 (72ms)  : 70, 74
    master - mean (72ms)  : 70, 75

    section Bailout
    This PR (8338) - mean (76ms)  : 74, 78
    master - mean (76ms)  : 74, 77

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,076ms)  : 1038, 1114
    master - mean (1,072ms)  : 1031, 1114

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 (112ms)  : 108, 115
    master - mean (115ms)  : 103, 127

    section Bailout
    This PR (8338) - mean (113ms)  : 110, 117
    master - mean (114ms)  : 110, 118

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (795ms)  : 772, 817
    master - mean (792ms)  : 774, 811

FakeDbCommand (.NET 6)

gantt
    title Execution time (ms) FakeDbCommand (.NET 6)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (99ms)  : 96, 102
    master - mean (98ms)  : 95, 101

    section Bailout
    This PR (8338) - mean (100ms)  : 97, 103
    master - mean (100ms)  : 98, 103

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (947ms)  : 908, 985
    master - mean (948ms)  : 916, 979

FakeDbCommand (.NET 8)

gantt
    title Execution time (ms) FakeDbCommand (.NET 8)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (99ms)  : 95, 103
    master - mean (99ms)  : 96, 102

    section Bailout
    This PR (8338) - mean (100ms)  : 97, 102
    master - mean (100ms)  : 98, 102

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (829ms)  : 792, 867
    master - mean (832ms)  : 788, 875

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 (205ms)  : 199, 212
    master - mean (212ms)  : 207, 218

    section Bailout
    This PR (8338) - mean (210ms)  : 204, 216
    master - mean (217ms)  : 211, 222

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,204ms)  : 1147, 1261
    master - mean (1,250ms)  : 1193, 1306

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 (297ms)  : 290, 303
    master - mean (309ms)  : 299, 318

    section Bailout
    This PR (8338) - mean (297ms)  : 289, 305
    master - mean (312ms)  : 302, 321

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (992ms)  : 967, 1017
    master - mean (1,027ms)  : 999, 1056

HttpMessageHandler (.NET 6)

gantt
    title Execution time (ms) HttpMessageHandler (.NET 6)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (289ms)  : 281, 297
    master - mean (301ms)  : 293, 310

    section Bailout
    This PR (8338) - mean (288ms)  : 281, 294
    master - mean (303ms)  : 293, 312

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,148ms)  : 1101, 1194
    master - mean (1,201ms)  : 1165, 1238

HttpMessageHandler (.NET 8)

gantt
    title Execution time (ms) HttpMessageHandler (.NET 8)
    dateFormat  x
    axisFormat %Q
    todayMarker off
    section Baseline
    This PR (8338) - mean (264ms)  : 260, 267
    master - mean (301ms)  : 294, 308

    section Bailout
    This PR (8338) - mean (264ms)  : 261, 266
    master - mean (302ms)  : 296, 308

    section CallTarget+Inlining+NGEN
    This PR (8338) - mean (1,026ms)  : 984, 1067
    master - mean (1,131ms)  : 1010, 1253

github-actions bot added the area:profiler Issues related to the continous-profiler label Mar 19, 2026

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 mentioned this pull request Mar 24, 2026

[Profiler] Add support for ARM64 back to the .NET profiler or allow enabling experimental feature. #3063

Open

gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch 2 times, most recently from d0d4a05 to 4f8778f Compare March 26, 2026 02:55

gleocadie added 15 commits March 27, 2026 22:35

Add HybridUnwinder for ARM64 only

637b6a0

Add CI job

24b3d1b

Make sure profiler is not disabled in the code

6dccf06

Fix path construction when running the integration tests

582a053

Fix bug in ManagedCodeCache

b27fc64

Fix native loader

639b5ec

Fix tracer/profiler test

7d384e6

Fix bugs

8297cd3

Fix framework for test + check lr-fallback approach

229f771

Make it better

bfd0286

Display in CI stack mismatch

b20eba4

Try fixing stack walking with jit stub/helper

6564543

Try fixing net9 issue with stack collection

61eaf3e

Try something: more native frames mixed with managed frames

3b4927a

Fix deadlock

24a5853

gleocadie added 4 commits March 27, 2026 22:35

Try fixing crash in libunwind

23e33e1

TO run CI

8dac27c

Add UnwindTracer

f18da89

Fix build + adjust libunwind mirrored data structures

afa59c9

gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch from a1216d9 to afa59c9 Compare March 27, 2026 22:35

gleocadie added 2 commits March 28, 2026 00:17

Try another one fix

c4e6e90

Try my fix

18fe7a4

gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch 6 times, most recently from 5e0a51e to 876012b Compare March 30, 2026 08:18

Try something else with UnwindTracersProvider

774f6b9

gleocadie force-pushed the gleocadie/add-frame-based-pointer-unwinding-for-arm64 branch from 876012b to 774f6b9 Compare March 30, 2026 23:24

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Profiler] Add support for ARM64#8338

[Profiler] Add support for ARM64#8338
gleocadie wants to merge 22 commits intomasterfrom
gleocadie/add-frame-based-pointer-unwinding-for-arm64

gleocadie commented Mar 19, 2026

Uh oh!

pr-commenter bot commented Mar 19, 2026 •

edited

Loading

Explanation

More details about the CI and significant changes

Uh oh!

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

edited

Loading

FakeDbCommand

HttpMessageHandler

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

gleocadie commented Mar 19, 2026

Summary of changes

Reason for change

Implementation details

Test coverage

Other details

Uh oh!

pr-commenter bot commented Mar 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Benchmarks

Explanation

More details about the CI and significant changes

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

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

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

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

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

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

scenario:Benchmarks.Trace.CharSliceBenchmark.OriginalCharSlice net472

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

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

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

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

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

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

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

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

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

Uh oh!

dd-trace-dotnet-ci-bot bot commented Mar 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Execution-Time Benchmarks Report ⏱️

FakeDbCommand

HttpMessageHandler

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

pr-commenter bot commented Mar 19, 2026 •

edited

Loading

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

edited

Loading