dotnet / dotnet/perf-autofiling-issues

[Perf] Linux/arm64: 55 Improvements on 7/13/2026 8:32:42 PM +00:00

Open
#76,362 2 comments 0 reactions 0 assignees View on GitHub
arch-arm64 bdn-update branch-refs/heads/main compilationmode-tiered kind-micro Look Again os-linux perf-improvement r2rtype-r2r_interpreter runkind-micro runtime-coreclr untriaged
Dominant language
No language data
Stars
10
Forks
8
PR metrics pending

Description

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [a90733cc40d6c7037a37d9c2b5c2403b8cac490f](https://github.com/dotnet/runtime/commit/a90733cc40d6c7037a37d9c2b5c2403b8cac490f)
Compare | [f2b30309fd488f1c3fd41c18723a7c80a81f4c67](https://github.com/dotnet/runtime/commit/f2b30309fd488f1c3fd41c18723a7c80a81f4c67)
Diff | [Diff](https://github.com/dotnet/runtime/compare/a90733cc40d6c7037a37d9c2b5c2403b8cac490f...f2b30309fd488f1c3fd41c18723a7c80a81f4c67)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in System.IO.Tests.Perf_FileStream

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

  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 400.50 ms | 112.53 ms | 0.28 | 0.76 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 3.66 ms | 1.34 ms | 0.37 | 0.71 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 7.42 ms | 2.82 ms | 0.38 | 0.79 | False | | |
|
  • [ReadAsync_NoBuffering - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 136.51 ms | 51.92 ms | 0.38 | 0.72 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 406.88 ms | 156.76 ms | 0.39 | 0.73 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 3.91 ms | 1.53 ms | 0.39 | 0.75 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 53.52 μs | 25.81 μs | 0.48 | 0.54 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 50.40 μs | 25.40 μs | 0.50 | 0.51 | False | | |
|
  • [ReadAsync_NoBuffering - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 103.77 ms | 53.29 ms | 0.51 | 0.70 | False | | |
|
  • [ReadAsync_NoBuffering - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 1050.99 μs | 551.20 μs | 0.52 | 0.65 | False | | |
|
  • [WriteAsync_NoBuffering_PreallocationSize - Duration of single invocation]()
  • [ADX - Test Multi Config Graph]()
| 2.17 ms | 1.23 ms | 0.57 | 0.58 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.75 ms | 2.92 ms | 0.62 | 0.81 | False | | |
|
  • [WriteAsync_NoBuffering_PreallocationSize - Duration of single invocation]()
  • [ADX - Test Multi Config Graph]()
| 183.49 ms | 115.11 ms | 0.63 | 0.55 | False | | |
|
  • [AppendAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.75 ms | 3.04 ms | 0.64 | 0.71 | False | | |
|
  • [WriteAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 474.87 ms | 351.16 ms | 0.74 | 0.73 | False | | |
|
  • [WriteAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 460.16 ms | 378.87 ms | 0.82 | 0.79 | False | | |

![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![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.IO.Tests.Perf_FileStream*'
```

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 104857600, userBufferSize: 4096, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 1048576, userBufferSize: 4096, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 1048576, userBufferSize: 512, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync_NoBuffering(fileSize: 104857600, userBufferSize: 16384, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 104857600, userBufferSize: 4096, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 1048576, userBufferSize: 4096, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 1024, userBufferSize: 1024, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 1024, userBufferSize: 1024, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync_NoBuffering(fileSize: 104857600, userBufferSize: 16384, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync_NoBuffering(fileSize: 1048576, userBufferSize: 16384, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.WriteAsync_NoBuffering_PreallocationSize(fileSize: 1048576, userBufferSize: 16384, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.ReadAsync(fileSize: 1048576, userBufferSize: 512, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.WriteAsync_NoBuffering_PreallocationSize(fileSize: 104857600, userBufferSize: 16384, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.AppendAsync(fileSize: 1048576, userBufferSize: 4096, options: DeleteOnClose, Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.WriteAsync(fileSize: 104857600, userBufferSize: 4096, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_FileStream.WriteAsync(fileSize: 104857600, userBufferSize: 4096, options: Asynchronous)

#### 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

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [a90733cc40d6c7037a37d9c2b5c2403b8cac490f](https://github.com/dotnet/runtime/commit/a90733cc40d6c7037a37d9c2b5c2403b8cac490f)
Compare | [f2b30309fd488f1c3fd41c18723a7c80a81f4c67](https://github.com/dotnet/runtime/commit/f2b30309fd488f1c3fd41c18723a7c80a81f4c67)
Diff | [Diff](https://github.com/dotnet/runtime/compare/a90733cc40d6c7037a37d9c2b5c2403b8cac490f...f2b30309fd488f1c3fd41c18723a7c80a81f4c67)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in System.IO.Tests.Perf_RandomAccess

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

  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.20 ms | 1.35 ms | 0.32 | 0.61 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 3.72 ms | 1.34 ms | 0.36 | 0.67 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 109.92 ms | 49.52 ms | 0.45 | 0.71 | False | | |
|
  • [ReadAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 96.14 ms | 53.87 ms | 0.56 | 0.69 | False | | |
|
  • [ReadScatterAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 49.63 ms | 29.25 ms | 0.59 | 0.48 | False | | |
|
  • [ReadScatterAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 50.77 ms | 30.36 ms | 0.60 | 0.52 | False | | |
|
  • [WriteAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 297.41 ms | 194.16 ms | 0.65 | 0.73 | False | | |
|
  • [ReadScatterAsync - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 1210.37 μs | 841.00 μs | 0.69 | 0.65 | False | | |

![graph]()
![graph]()
![graph]()
![graph]()
![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.IO.Tests.Perf_RandomAccess*'
```

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 1048576, bufferSize: 4096, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 1048576, bufferSize: 4096, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 104857600, bufferSize: 16384, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 104857600, bufferSize: 16384, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadScatterAsync(fileSize: 104857600, buffersSize: 65536, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadScatterAsync(fileSize: 104857600, buffersSize: 65536, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.WriteAsync(fileSize: 104857600, bufferSize: 16384, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadScatterAsync(fileSize: 1048576, buffersSize: 16384, options: Asynchronous)

#### 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

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [a90733cc40d6c7037a37d9c2b5c2403b8cac490f](https://github.com/dotnet/runtime/commit/a90733cc40d6c7037a37d9c2b5c2403b8cac490f)
Compare | [f2b30309fd488f1c3fd41c18723a7c80a81f4c67](https://github.com/dotnet/runtime/commit/f2b30309fd488f1c3fd41c18723a7c80a81f4c67)
Diff | [Diff](https://github.com/dotnet/runtime/compare/a90733cc40d6c7037a37d9c2b5c2403b8cac490f...f2b30309fd488f1c3fd41c18723a7c80a81f4c67)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in System.Net.Http.Tests.SocketsHttpHandlerPerfTest

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

  • [Get - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 138.63 μs | 64.58 μs | 0.47 | 0.37 | False | | |
|
  • [Get_EnumerateHeaders_Validated - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 145.68 μs | 90.04 μs | 0.62 | 0.35 | False | | |
|
  • [Get - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 141.28 μs | 88.99 μs | 0.63 | 0.38 | False | | |
|
  • [Get_EnumerateHeaders_Unvalidated - Duration of single invocation]()
  • [ADX - Test Multi Config Graph]()
| 136.68 μs | 87.35 μs | 0.64 | 0.34 | False | | |
|
  • [Get_EnumerateHeaders_Unvalidated - Duration of single invocation]()
  • [ADX - Test Multi Config Graph]()
| 140.64 μs | 91.10 μs | 0.65 | 0.40 | False | | |
|
  • [Get_EnumerateHeaders_Validated - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 143.93 μs | 93.58 μs | 0.65 | 0.40 | False | | |

![graph]()
![graph]()
![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.Net.Http.Tests.SocketsHttpHandlerPerfTest*'
```

### System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get(ssl: False, chunkedResponse: True, responseLength: 1)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated(ssl: False, chunkedResponse: True, responseLength: 1)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get(ssl: False, chunkedResponse: False, responseLength: 1)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: False, chunkedResponse: True, responseLength: 1)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Unvalidated(ssl: False, chunkedResponse: False, responseLength: 1)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Net.Http.Tests.SocketsHttpHandlerPerfTest.Get_EnumerateHeaders_Validated(ssl: False, chunkedResponse: False, responseLength: 1)

#### 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)

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the benchmark source in src/benchmarks/micro/libraries/System.IO.FileSystem/Perf.FileStream.cs at lines 280-290, then compare the linked baseline and test reports for the ARM64 AzureLinux configuration. The report does not specify a code change or success criterion, so completion would require triage to identify an actionable cause and define how it should be verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp
Domain
performance
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.