Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Perf measurement changed due to BDN update #66664

Closed
performanceautofiler bot opened this issue Mar 15, 2022 · 14 comments
Closed

Perf measurement changed due to BDN update #66664

performanceautofiler bot opened this issue Mar 15, 2022 · 14 comments
Assignees
Labels
arch-x64 area-GC-coreclr os-linux Linux OS (any supported distro) runtime-coreclr specific to the CoreCLR runtime
Milestone

Comments

@performanceautofiler
Copy link

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in PerfLabTests.LowLevelPerf

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GenericClassGenericInstanceMethod - Duration of single invocation 108.79 μs 152.27 μs 1.40 0.09 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'PerfLabTests.LowLevelPerf*'

Payloads

Baseline
Compare

Histogram

PerfLabTests.LowLevelPerf.GenericClassGenericInstanceMethod


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 152.26848763069455 > 114.1891593163228.
IsChangePoint: Marked as a change because one of 2/1/2022 8:13:55 AM, 2/7/2022 5:30:00 PM, 2/19/2022 11:51:48 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -18.411230076485225 (T) = (0 -152339.69703271738) / Math.Sqrt((215043981.29227346 / (50)) + (30962.15348726156 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.33459358592612964 = (114146.88234621071 - 152339.69703271738) / 114146.88234621071 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

### Run Information
Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DivisionOperatorBenchmark - Duration of single invocation 19.33 ns 21.34 ns 1.10 0.10 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt32>.DivisionOperatorBenchmark


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 21.343080974054562 > 20.609751481219558.
IsChangePoint: Marked as a change because one of 2/4/2022 6:00:25 PM, 3/3/2022 10:59:13 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -2.5818159065022552 (T) = (0 -21.613150255722033) / Math.Sqrt((4.7361616956054595 / (50)) + (3.3162067500162973 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.0760236823856467 = (20.08612878092388 - 21.613150255722033) / 20.08612878092388 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Diagnostics.Perf_Activity

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ActivityAllocations - Duration of single invocation 209.43 ns 233.36 ns 1.11 0.07 False
EnumerateActivityLinkTagsSmall - Duration of single invocation 52.71 ns 56.77 ns 1.08 0.02 False

graph
graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Diagnostics.Perf_Activity*'

Payloads

Baseline
Compare

Histogram

System.Diagnostics.Perf_Activity.ActivityAllocations(idFormat: W3C)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 233.36223175128367 > 216.16422674283905.
IsChangePoint: Marked as a change because one of 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -8.621022864458252 (T) = (0 -228.94307270766475) / Math.Sqrt((32.078697121602765 / (50)) + (79.54763117655831 / (12))) is less than -2.0002978220134566 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (12) - 2, .025) and -0.11300910532417982 = (205.6973942194137 - 228.94307270766475) / 205.6973942194137 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Diagnostics.Perf_Activity.EnumerateActivityLinkTagsSmall

```log

Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 56.765787305067256 > 55.25313766355957.
IsChangePoint: Marked as a change because one of 1/19/2022 3:47:09 AM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -24.40328217355822 (T) = (0 -56.59224771724442) / Math.Sqrt((0.7261720972172016 / (50)) + (0.05103723337957388 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.062214930877315756 = (53.27758636428049 - 56.59224771724442) / 53.27758636428049 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Collections.CtorGivenSize<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Stack - Duration of single invocation 133.59 ns 147.84 ns 1.11 0.18 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.CtorGivenSize&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.CtorGivenSize<String>.Stack(Size: 512)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 147.84130488908252 > 142.5028238654394.
IsChangePoint: Marked as a change because one of 1/11/2022 2:18:34 PM, 1/18/2022 7:04:48 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -14.02701433603456 (T) = (0 -149.61656383692844) / Math.Sqrt((10.55722883064997 / (50)) + (7.107666420398533 / (12))) is less than -2.0002978220134566 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (12) - 2, .025) and -0.09174588306105283 = (137.04339641513587 - 149.61656383692844) / 137.04339641513587 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

@performanceautofiler performanceautofiler bot added CoreClr untriaged New issue has not been triaged by the area owner labels Mar 15, 2022
@EgorBo EgorBo changed the title [Perf] Changes at 3/12/2022 1:22:26 AM Perf measurement changed due to BDN update Mar 15, 2022
@dotnet-issue-labeler
Copy link

I couldn't figure out the best area label to add to this issue. If you have write-permissions please help me learn by adding exactly one area label.

@EgorBo EgorBo transferred this issue from dotnet/perf-autofiling-issues Mar 15, 2022
@EgorBo
Copy link
Member

EgorBo commented Mar 15, 2022

BDN update commit: dotnet/performance@035dde5

@EgorBo
Copy link
Member

EgorBo commented Mar 15, 2022

cc @adamsitnik

@EgorBo
Copy link
Member

EgorBo commented Mar 15, 2022

dotnet/perf-autofiling-issues#3986 is likely affected by dotnet/performance@742bc35 BDN update

@ghost
Copy link

ghost commented Mar 16, 2022

Tagging subscribers to this area: @dotnet/runtime-infrastructure
See info in area-owners.md if you want to be subscribed.

Issue Details

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in PerfLabTests.LowLevelPerf

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GenericClassGenericInstanceMethod - Duration of single invocation 108.79 μs 152.27 μs 1.40 0.09 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'PerfLabTests.LowLevelPerf*'

Payloads

Baseline
Compare

Histogram

PerfLabTests.LowLevelPerf.GenericClassGenericInstanceMethod


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 152.26848763069455 > 114.1891593163228.
IsChangePoint: Marked as a change because one of 2/1/2022 8:13:55 AM, 2/7/2022 5:30:00 PM, 2/19/2022 11:51:48 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -18.411230076485225 (T) = (0 -152339.69703271738) / Math.Sqrt((215043981.29227346 / (50)) + (30962.15348726156 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.33459358592612964 = (114146.88234621071 - 152339.69703271738) / 114146.88234621071 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

### Run Information
Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DivisionOperatorBenchmark - Duration of single invocation 19.33 ns 21.34 ns 1.10 0.10 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt32>.DivisionOperatorBenchmark


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 21.343080974054562 > 20.609751481219558.
IsChangePoint: Marked as a change because one of 2/4/2022 6:00:25 PM, 3/3/2022 10:59:13 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -2.5818159065022552 (T) = (0 -21.613150255722033) / Math.Sqrt((4.7361616956054595 / (50)) + (3.3162067500162973 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.0760236823856467 = (20.08612878092388 - 21.613150255722033) / 20.08612878092388 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Diagnostics.Perf_Activity

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ActivityAllocations - Duration of single invocation 209.43 ns 233.36 ns 1.11 0.07 False
EnumerateActivityLinkTagsSmall - Duration of single invocation 52.71 ns 56.77 ns 1.08 0.02 False

graph
graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Diagnostics.Perf_Activity*'

Payloads

Baseline
Compare

Histogram

System.Diagnostics.Perf_Activity.ActivityAllocations(idFormat: W3C)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 233.36223175128367 > 216.16422674283905.
IsChangePoint: Marked as a change because one of 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -8.621022864458252 (T) = (0 -228.94307270766475) / Math.Sqrt((32.078697121602765 / (50)) + (79.54763117655831 / (12))) is less than -2.0002978220134566 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (12) - 2, .025) and -0.11300910532417982 = (205.6973942194137 - 228.94307270766475) / 205.6973942194137 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Diagnostics.Perf_Activity.EnumerateActivityLinkTagsSmall

```log

Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 56.765787305067256 > 55.25313766355957.
IsChangePoint: Marked as a change because one of 1/19/2022 3:47:09 AM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -24.40328217355822 (T) = (0 -56.59224771724442) / Math.Sqrt((0.7261720972172016 / (50)) + (0.05103723337957388 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.062214930877315756 = (53.27758636428049 - 56.59224771724442) / 53.27758636428049 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Collections.CtorGivenSize<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Stack - Duration of single invocation 133.59 ns 147.84 ns 1.11 0.18 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.CtorGivenSize&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.CtorGivenSize<String>.Stack(Size: 512)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 147.84130488908252 > 142.5028238654394.
IsChangePoint: Marked as a change because one of 1/11/2022 2:18:34 PM, 1/18/2022 7:04:48 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -14.02701433603456 (T) = (0 -149.61656383692844) / Math.Sqrt((10.55722883064997 / (50)) + (7.107666420398533 / (12))) is less than -2.0002978220134566 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (12) - 2, .025) and -0.09174588306105283 = (137.04339641513587 - 149.61656383692844) / 137.04339641513587 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Author: performanceautofiler[bot]
Assignees: -
Labels:

area-Infrastructure, untriaged, refs/heads/main, ubuntu 18.04, RunKind=micro, Regression, CoreClr, x64

Milestone: -

@adamsitnik
Copy link
Member

PerfLabTests.LowLevelPerf.GenericClassGenericInstanceMethod seems to just have 3 modes:

image

System.Numerics.Tests.Perf_VectorOf(UInt32).DivisionOperatorBenchmark seems to get back to previous level?

image

System.Diagnostics.Perf_Activity is most likely caused by #66489 (cc @tarekgh):

image

diff

System.Collections.CtorGivenSize<String> also seems to be back to value that was reported for a while in the past:

image

@tarekgh
Copy link
Member

tarekgh commented Mar 16, 2022

@adamsitnik

System.Diagnostics.Perf_Activity is most likely caused by #66489

I doubt this will be the case. does adding a Boolean field can cause this regression?

@adamsitnik
Copy link
Member

@tarekgh I was able to confirm that one of the commits within the provided range has regressed perf:

git clone https://github.com/dotnet/runtime.git
cd runtime
git checkout 3e2d483153adcab27033340fa40ad0bcdc3acc2a
build.cmd -c Release -subset clr+libs
robocopy .\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\7.0.0\ .\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\baseline\ /E
git checkout 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
taskkill /IM "dotnet.exe" /F
build.cmd -c Release -subset clr+libs
robocopy .\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\7.0.0\ .\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\compare\ /E
cd ..
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net7.0 --filter 'System.Diagnostics.Perf_Activity.ActivityAllocations*' --corerun .\runtime\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\baseline\corerun.exe .\runtime\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\compare\corerun.exe 
Method Toolchain idFormat Mean Ratio Allocated Alloc Ratio
ActivityAllocations \baseline\corerun.exe Hierarchical 173.2 ns 1.00 344 B 1.00
ActivityAllocations \compare\corerun.exe Hierarchical 174.1 ns 1.01 352 B 1.02
ActivityAllocations \baseline\corerun.exe W3C 209.3 ns 1.00 408 B 1.00
ActivityAllocations \compare\corerun.exe W3C 233.4 ns 1.12 416 B 1.02

@tarekgh
Copy link
Member

tarekgh commented Mar 17, 2022

@adamsitnik thanks for confirming.

I have tried more, and I am seeing my commit #66489 is what caused the issue. But my change is just adding a property with a Boolean backend field to the Activity object. @EgorBo is this something you can help with looking why this is happening?

@EgorBo
Copy link
Member

EgorBo commented Mar 17, 2022

ARM64: dotnet/perf-autofiling-issues#4140
some of them might be GC Regions related (#64688)

@adamsitnik
Copy link
Member

adamsitnik commented Mar 18, 2022

@EgorBo is right, the regression is caused by GC regions (cc @mangod9).

To get ETW trace file I've extended the repro provided above (#66664 (comment)) with:

py .\performance\scripts\benchmarks_ci.py -f net7.0 --filter 'System.Diagnostics.Perf_Activity.ActivityAllocations*' --corerun .\runtime\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\baseline\corerun.exe .\runtime\artifacts\bin\testhost\net7.0-windows-Release-x64\shared\Microsoft.NETCore.App\compare\corerun.exe --bdn-arguments "--profiler ETW --iterationCount 15 --invocationCount 1096400 --keepFiles true"

To get the nice table included below: https://github.com/dotnet/performance/blob/main/docs/profiling-workflow-dotnet-runtime.md#identifying-regressions

Overweight report for symbols common between both files


Base (old) Time: 253.1
Test (new) Time: 292.6
Delta: 39.5
Delta %: 15.6

In this report, overweight is ratio of actual growth compared to 15.6%.
Interest level attempts to identify smaller methods which changed a lot. These are likely the most interesting frames to sart investigating
An overweight of greater than 100% indicates the symbol grew in cost more than average.
High overweights are a likely source of regressions and represent good places to investigate.
Only symbols that have at least 2% impact are shown.

Name Base Test Delta Responsibility % Overweight % Interest Level
coreclr!memset 7.0 39.0 32.0 81.02 2929.08 5
coreclr!WKS::gc_heap::a_fit_segment_end_p 10.0 48.0 38.0 96.22 2434.80 5
coreclr!WKS::gc_heap::adjust_limit_clr 10.0 47.0 37.0 93.68 2370.73 5
coreclr!WKS::gc_heap::allocate_soh 12.0 49.0 37.0 93.68 1975.61 5
coreclr!JIT_New 10.0 40.0 30.0 75.96 1922.21 5
coreclr!WKS::gc_heap::try_allocate_more_space 13.0 50.0 37.0 93.68 1823.64 5
coreclr!WKS::GCHeap::Alloc 13.0 50.0 37.0 93.68 1823.64 5
coreclr!WKS::gc_heap::allocate_more_space 13.0 50.0 37.0 93.68 1823.64 5
coreclr!Alloc 5.0 14.0 9.0 22.79 1153.33 5
coreclr!AllocateString 5.0 14.0 9.0 22.79 1153.33 5
coreclr!FramedAllocateString 6.0 15.0 9.0 22.79 961.11 5
System.Private.CoreLib.il!System.Threading.ExecutionContext.SetLocalValue(class System.Threading.IAsyncLocal,class System.Object,bool) 21.0 40.0 19.0 48.11 579.71 5
microbenchmarks!System.Diagnostics.Perf_Activity.ActivityAllocations(value class System.Diagnostics.ActivityIdFormat) 177.7 221.5 43.8 110.88 157.92 5
system.diagnostics.diagnosticsource!System.Diagnostics.Activity.Stop() 53.0 41.0 -12.0 -30.38 -145.07 5
coreclr!??WKS::gc_heap::fire_etw_allocation_event 1.0 7.0 6.0 15.19 3844.42 4
coreclr!GCToCLREventSink::FireGCAllocationTick_V4 1.0 7.0 6.0 15.19 3844.42 4
coreclr!CEEInfo::reportInliningDecision 1.0 6.0 5.0 12.66 3203.69 4
coreclr!TypeHandle::GetName 1.0 3.0 2.0 5.06 1281.47 4
coreclr!JIT_TrialAllocSFastMP_InlineGetThread 6.0 10.0 4.0 10.13 427.16 4
coreclr!JIT_GetSharedGCThreadStaticBase 21.0 26.0 5.0 12.66 152.56 4
system.diagnostics.diagnosticsource!System.Diagnostics.Activity.Start() 165.7 187.5 21.8 55.18 84.28 4
System.Private.CoreLib.il!System.DateTime.get_UtcNow() 91.7 83.0 -8.7 -21.97 -60.64 4
?!? 7.0 5.0 -2.0 -5.06 -183.07 4
system.diagnostics.diagnosticsource!System.Diagnostics.RandomNumberGenerator.get_Current() 13.0 9.0 -4.0 -10.13 -197.15 4
coreclr!AllocateStringFastMP_InlineGetThread 9.0 2.0 -7.0 -17.72 -498.35 4
coreclr!CEEInfo::runWithErrorTrap 5.0 1.0 -4.0 -10.13 -512.59 4
coreclr!MethodTable::_GetFullyQualifiedNameForClass 1.0 2.0 1.0 2.53 640.74 3
coreclr!`eh vector destructor iterator' 1.0 2.0 1.0 2.53 640.74 3
coreclr!SString::~SString 1.0 2.0 1.0 2.53 640.74 3
coreclr!__security_check_cookie 2.0 3.0 1.0 2.53 320.37 3
coreclr!JIT_WriteBarrier 3.0 4.0 1.0 2.53 213.58 3
System.Private.CoreLib.il!System.Threading.AsyncLocal`1[System.__Canon].get_Value() 8.0 9.5 1.5 3.72 117.68 3
ROOT 253.1 292.6 39.5 100.00 100.00 3
system.private.corelib!? 236.1 272.6 36.5 92.40 99.06 3
coreclr!CallDescrWorkerInternal 236.1 272.6 36.5 92.40 99.06 3
coreclr!MethodDescCallSite::CallTargetWorker 236.1 272.6 36.5 92.40 99.06 3
coreclr!CallDescrWorkerReflectionWrapper 236.1 272.6 36.5 92.40 99.06 3
benchmarkdotnet!BenchmarkDotNet.Engines.Engine.Run() 236.1 272.6 36.5 92.40 99.06 3
benchmarkdotnet!BenchmarkDotNet.Engines.EngineActualStage.RunWorkload(int64,int32,bool) 236.1 272.6 36.5 92.40 99.06 3
coreclr!Assembly::ExecuteMainMethod 236.1 272.6 36.5 92.40 99.06 3
coreclr!CorHost2::ExecuteAssembly 236.1 272.6 36.5 92.40 99.06 3
coreclr!coreclr_execute_assembly 236.1 272.6 36.5 92.40 99.06 3
benchmarkdotnet!BenchmarkDotNet.Engines.EngineActualStage.Run(int64,value class BenchmarkDotNet.Engines.IterationMode,bool,int32,bool) 236.1 272.6 36.5 92.40 99.06 3
coreclr!RunMainInternal 236.1 272.6 36.5 92.40 99.06 3
benchmarkdotnet!BenchmarkDotNet.Engines.EngineActualStage.RunSpecific(int64,value class BenchmarkDotNet.Engines.IterationMode,int32,int32) 236.1 272.6 36.5 92.40 99.06 3
benchmarkdotnet!BenchmarkDotNet.Engines.Engine.RunIteration(value class BenchmarkDotNet.Engines.IterationData) 236.1 272.6 36.5 92.40 99.06 3
coreclr!RunMain 236.1 272.6 36.5 92.40 99.06 3
coreclr!RuntimeMethodHandle::InvokeMethod 236.1 272.6 36.5 92.40 99.06 3
coreclr!??MethodDesc::JitCompileCodeLockedEventWrapper 16.0 18.0 2.0 5.06 80.09 3
coreclr!TieredCompilationManager::BackgroundWorkerStart 17.0 19.0 2.0 5.06 75.38 3
coreclr!TieredCompilationManager::BackgroundWorkerBootstrapper0 17.0 19.0 2.0 5.06 75.38 3
coreclr!ManagedThreadBase_DispatchOuter 17.0 19.0 2.0 5.06 75.38 3
coreclr!TieredCompilationManager::DoBackgroundWork 17.0 19.0 2.0 5.06 75.38 3
coreclr!TieredCompilationManager::BackgroundWorkerBootstrapper1 17.0 19.0 2.0 5.06 75.38 3
coreclr!ManagedThreadBase_DispatchMiddle 17.0 19.0 2.0 5.06 75.38 3
system.diagnostics.diagnosticsource!System.HexConverter.ToString(value class System.ReadOnlySpan`1,value class Casing) 66.0 64.0 -2.0 -5.06 -19.42 3
system.diagnostics.diagnosticsource!System.Diagnostics.Activity.GenerateW3CId() 96.0 92.0 -4.0 -10.13 -26.70 3
system.diagnostics.diagnosticsource!System.Diagnostics.ActivityTraceId.CreateFromBytes(value class System.ReadOnlySpan`1) 47.0 45.0 -2.0 -5.06 -27.27 3
ntdll!RtlQueryPerformanceCounter 51.7 48.0 -3.7 -9.31 -45.59 3
system.diagnostics.diagnosticsource!System.Diagnostics.ActivitySpanId.CreateRandom() 40.0 37.0 -3.0 -7.60 -48.06 3
system.diagnostics.diagnosticsource!System.Diagnostics.ActivityTraceId.CreateRandom() 53.0 49.0 -4.0 -10.13 -48.36 3
coreclr!WKS::gc_heap::mark_phase 1.0 0.1 -0.9 -2.32 -588.26 3
coreclr!WKS::GCHeap::GarbageCollectGeneration 1.4 0.1 -1.3 -3.29 -602.71 3
coreclr!WKS::gc_heap::garbage_collect 1.4 0.1 -1.3 -3.29 -602.71 3
coreclr!WKS::gc_heap::gc1 1.4 0.1 -1.3 -3.29 -602.71 3
ntdll!RtlUserThreadStart 253.1 291.6 38.5 97.47 97.47 2
coreclr!MethodDesc::JitCompileCodeLocked 16.0 17.0 1.0 2.53 40.05 2
coreclr!UnsafeJitFunction 16.0 17.0 1.0 2.53 40.05 2
coreclr!MethodDesc::PrepareILBasedCode 17.0 18.0 1.0 2.53 37.69 2
coreclr!TieredCompilationManager::CompileCodeVersion 17.0 18.0 1.0 2.53 37.69 2
coreclr!MethodDesc::JitCompileCode 17.0 18.0 1.0 2.53 37.69 2
System.Private.CoreLib.il!System.String.Create(int32,!!0,class System.Buffers.SpanAction`2) 63.0 62.0 -1.0 -2.53 -10.17 2

@ghost
Copy link

ghost commented Mar 21, 2022

Tagging subscribers to this area: @dotnet/gc
See info in area-owners.md if you want to be subscribed.

Issue Details

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in PerfLabTests.LowLevelPerf

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GenericClassGenericInstanceMethod - Duration of single invocation 108.79 μs 152.27 μs 1.40 0.09 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'PerfLabTests.LowLevelPerf*'

Payloads

Baseline
Compare

Histogram

PerfLabTests.LowLevelPerf.GenericClassGenericInstanceMethod


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 152.26848763069455 > 114.1891593163228.
IsChangePoint: Marked as a change because one of 2/1/2022 8:13:55 AM, 2/7/2022 5:30:00 PM, 2/19/2022 11:51:48 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -18.411230076485225 (T) = (0 -152339.69703271738) / Math.Sqrt((215043981.29227346 / (50)) + (30962.15348726156 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.33459358592612964 = (114146.88234621071 - 152339.69703271738) / 114146.88234621071 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

### Run Information
Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DivisionOperatorBenchmark - Duration of single invocation 19.33 ns 21.34 ns 1.10 0.10 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt32>.DivisionOperatorBenchmark


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 21.343080974054562 > 20.609751481219558.
IsChangePoint: Marked as a change because one of 2/4/2022 6:00:25 PM, 3/3/2022 10:59:13 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -2.5818159065022552 (T) = (0 -21.613150255722033) / Math.Sqrt((4.7361616956054595 / (50)) + (3.3162067500162973 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.0760236823856467 = (20.08612878092388 - 21.613150255722033) / 20.08612878092388 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Diagnostics.Perf_Activity

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ActivityAllocations - Duration of single invocation 209.43 ns 233.36 ns 1.11 0.07 False
EnumerateActivityLinkTagsSmall - Duration of single invocation 52.71 ns 56.77 ns 1.08 0.02 False

graph
graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Diagnostics.Perf_Activity*'

Payloads

Baseline
Compare

Histogram

System.Diagnostics.Perf_Activity.ActivityAllocations(idFormat: W3C)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 233.36223175128367 > 216.16422674283905.
IsChangePoint: Marked as a change because one of 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -8.621022864458252 (T) = (0 -228.94307270766475) / Math.Sqrt((32.078697121602765 / (50)) + (79.54763117655831 / (12))) is less than -2.0002978220134566 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (12) - 2, .025) and -0.11300910532417982 = (205.6973942194137 - 228.94307270766475) / 205.6973942194137 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Diagnostics.Perf_Activity.EnumerateActivityLinkTagsSmall

```log

Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 56.765787305067256 > 55.25313766355957.
IsChangePoint: Marked as a change because one of 1/19/2022 3:47:09 AM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -24.40328217355822 (T) = (0 -56.59224771724442) / Math.Sqrt((0.7261720972172016 / (50)) + (0.05103723337957388 / (13))) is less than -1.9996235849941724 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (13) - 2, .025) and -0.062214930877315756 = (53.27758636428049 - 56.59224771724442) / 53.27758636428049 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Run Information

Architecture x64
OS ubuntu 18.04
Baseline 3e2d483153adcab27033340fa40ad0bcdc3acc2a
Compare 6e26872d0a282aa71ea792c3550a3cb0e8bf4e71
Diff Diff

Regressions in System.Collections.CtorGivenSize<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Stack - Duration of single invocation 133.59 ns 147.84 ns 1.11 0.18 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.CtorGivenSize&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.CtorGivenSize<String>.Stack(Size: 512)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 147.84130488908252 > 142.5028238654394.
IsChangePoint: Marked as a change because one of 1/11/2022 2:18:34 PM, 1/18/2022 7:04:48 PM, 3/11/2022 8:42:43 PM, 3/15/2022 12:53:39 AM falls between 3/6/2022 12:59:26 AM and 3/15/2022 12:53:39 AM.
IsRegressionStdDev: Marked as regression because -14.02701433603456 (T) = (0 -149.61656383692844) / Math.Sqrt((10.55722883064997 / (50)) + (7.107666420398533 / (12))) is less than -2.0002978220134566 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (50) + (12) - 2, .025) and -0.09174588306105283 = (137.04339641513587 - 149.61656383692844) / 137.04339641513587 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

Author: performanceautofiler[bot]
Assignees: -
Labels:

area-GC-coreclr, untriaged, refs/heads/main, ubuntu 18.04, RunKind=micro, Regression, CoreClr, x64

Milestone: -

@mangod9 mangod9 removed the untriaged New issue has not been triaged by the area owner label Jul 6, 2022
@mangod9 mangod9 added this to the 7.0.0 milestone Jul 6, 2022
@mrsharm mrsharm self-assigned this Aug 1, 2022
@cshung cshung removed their assignment Aug 2, 2022
@mrsharm mrsharm modified the milestones: 7.0.0, 8.0.0 Aug 8, 2022
@mrsharm
Copy link
Member

mrsharm commented Aug 8, 2022

Attribute these GC related regressions to the decommit behavior for regions that's being tracked; #73592 & updated the milestone.

@jeffhandley jeffhandley added runtime-coreclr specific to the CoreCLR runtime os-linux Linux OS (any supported distro) arch-x64 and removed CoreClr labels Dec 28, 2022
@mrsharm
Copy link
Member

mrsharm commented Aug 5, 2023

Closing in lieu of #73592 with the latest Net 8.0 results.

@mrsharm mrsharm closed this as completed Aug 5, 2023
@ghost ghost locked as resolved and limited conversation to collaborators Sep 4, 2023
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
arch-x64 area-GC-coreclr os-linux Linux OS (any supported distro) runtime-coreclr specific to the CoreCLR runtime
Projects
None yet
Development

No branches or pull requests

9 participants