[Perf] Linux/arm64: 29 Regressions on 7/13/2026 11:30:22 AM +00:00

Open

#76,331 opened on Jul 16, 2026 2 comments 0 reactions 0 assignees View on GitHub

arch-arm64 branch-refs/heads/main compilationmode-tiered kind-micro Look Again os-linux perf-regression r2rtype-r2r_interpreter runkind-micro runtime-coreclr untriaged

Dominant language: No language data
Stars: 10
Forks: 8
PR merge metrics: PR metrics pending

Description

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [010acabe079d1bd50f838de34e9815f81d977469](https://github.com/dotnet/runtime/commit/010acabe079d1bd50f838de34e9815f81d977469)
Compare | [8a5301832157c4740b8c85ee25086762b29af531](https://github.com/dotnet/runtime/commit/8a5301832157c4740b8c85ee25086762b29af531)
Diff | [Diff](https://github.com/dotnet/runtime/compare/010acabe079d1bd50f838de34e9815f81d977469...8a5301832157c4740b8c85ee25086762b29af531)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<MyEventsListerViewModel>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 914.11 μs | 1268.65 μs | 1.39 | 0.13 | False | | |
|

[DeserializeFromUtf8Bytes - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 913.69 μs | 1258.66 μs | 1.38 | 0.09 | False | | |
|

[DeserializeFromStream - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 992.25 μs | 1324.13 μs | 1.33 | 0.16 | False | | |
|

[DeserializeFromReader - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.05 ms | 1.39 ms | 1.32 | 0.10 | False | | |

![graph]()
![graph]()
![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<MyEventsListerViewModel>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<MyEventsListerViewModel>.DeserializeFromUtf8Bytes(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<MyEventsListerViewModel>.DeserializeFromStream(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<MyEventsListerViewModel>.DeserializeFromReader(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

[Profiling workflow for dotnet/runtime repository](https://github.com/dotnet/performance/blob/master/docs/profiling-workflow-dotnet-runtime.md)
[Benchmarking workflow for dotnet/runtime repository](https://github.com/dotnet/performance/blob/master/docs/benchmarking-workflow-dotnet-runtime.md)

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<TreeRecord>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromUtf8Bytes - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 119.13 μs | 142.17 μs | 1.19 | 0.13 | False | | |
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 119.71 μs | 141.09 μs | 1.18 | 0.10 | False | | |
|

[DeserializeFromStream - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 123.27 μs | 145.26 μs | 1.18 | 0.17 | False | | |

![graph]()
![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<TreeRecord>.DeserializeFromUtf8Bytes(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<TreeRecord>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<TreeRecord>.DeserializeFromStream(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<LoginViewModel>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromUtf8Bytes - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.61 μs | 1.92 μs | 1.19 | 0.16 | False | | |
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.71 μs | 1.98 μs | 1.16 | 0.10 | False | | |
|

[DeserializeFromReader - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 2.03 μs | 2.34 μs | 1.15 | 0.13 | False | | |

![graph]()
![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<LoginViewModel>.DeserializeFromUtf8Bytes(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<LoginViewModel>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<LoginViewModel>.DeserializeFromReader(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<LargeStructWithProperties>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromStream - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 5.45 μs | 8.37 μs | 1.53 | 0.17 | False | | |
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 4.35 μs | 5.62 μs | 1.29 | 0.09 | False | | |
|

[DeserializeFromReader - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 5.08 μs | 6.31 μs | 1.24 | 0.12 | False | | |

![graph]()
![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<LargeStructWithProperties>.DeserializeFromStream(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<LargeStructWithProperties>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<LargeStructWithProperties>.DeserializeFromReader(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<Location>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromReader - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 4.99 μs | 6.33 μs | 1.27 | 0.13 | False | | |
|

[DeserializeFromStream - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 5.63 μs | 7.13 μs | 1.27 | 0.10 | False | | |
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 4.43 μs | 5.42 μs | 1.22 | 0.10 | False | | |

![graph]()
![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<Location>.DeserializeFromReader(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<Location>.DeserializeFromStream(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<Location>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<ClassRecord>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromUtf8Bytes - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.96 μs | 2.30 μs | 1.17 | 0.10 | False | | |
|

[DeserializeFromReader - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 2.56 μs | 2.97 μs | 1.16 | 0.08 | False | | |

![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<ClassRecord>.DeserializeFromUtf8Bytes(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<ClassRecord>.DeserializeFromReader(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<SimpleStructWithProperties>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.26 μs | 1.43 μs | 1.13 | 0.11 | False | | |
|

[DeserializeFromUtf8Bytes - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 1.22 μs | 1.38 μs | 1.13 | 0.17 | False | | |

![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<SimpleStructWithProperties>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<SimpleStructWithProperties>.DeserializeFromUtf8Bytes(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadJson<IndexViewModel>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[DeserializeFromString - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 87.23 μs | 109.09 μs | 1.25 | 0.10 | False | | |
|

[DeserializeFromUtf8Bytes - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 85.32 μs | 105.17 μs | 1.23 | 0.10 | False | | |

![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadJson*'
```

### System.Text.Json.Serialization.Tests.ReadJson<IndexViewModel>.DeserializeFromString(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadJson<IndexViewModel>.DeserializeFromUtf8Bytes(Mode: Reflection)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in System.Text.Json.Serialization.Tests.ReadMissingAndCaseInsensitive<Location>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[Baseline - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 4.48 μs | 5.50 μs | 1.23 | 0.13 | False | | |
|

[CaseInsensitiveNotMatching - Duration of single invocation]()
📝 - [Benchmark Source]()
[ADX - Test Multi Config Graph]()

| 4.50 μs | 5.41 μs | 1.20 | 0.11 | False | | |

![graph]()
![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.ReadMissingAndCaseInsensitive*'
```

### System.Text.Json.Serialization.Tests.ReadMissingAndCaseInsensitive<Location>.Baseline

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Text.Json.Serialization.Tests.ReadMissingAndCaseInsensitive<Location>.CaseInsensitiveNotMatching

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

---

### Run Information

### Regressions in MicroBenchmarks.Serializers.Json_FromStream<LoginViewModel>

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

[SystemTextJson_Reflection_ - Duration of single invocation]()
[ADX - Test Multi Config Graph]()

| 1.91 μs | 2.26 μs | 1.18 | 0.11 | False | | |

![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'MicroBenchmarks.Serializers.Json_FromStream*'
```

### MicroBenchmarks.Serializers.Json_FromStream<LoginViewModel>.SystemTextJson_Reflection_

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with src/benchmarks/micro/libraries/System.Text.Json/Serializer/ReadJson.cs lines 66-89 and reproduce with scripts/benchmarks_ci.py using the supplied filter. Compare the arm64 AzureLinux results with the baseline and compare commits; done means identifying the regression cause and restoring the affected benchmark timings.

Written by the indexing model from the issue text.

Assessment

Tech stack: azure, linux, python
Domain: performance, testing
Issue type: Bug
Difficulty: 4/5
Estimated time: 3-5 days
Activity status: Quiet
Clarity: Mostly clear
Newbie friendliness: 45/100

[Perf] Linux/arm64: 29 Regressions on 7/13/2026 11:30:22 AM +00:00

Description

Contributor guide

Research direction

Assessment

Get new issues in your inbox