[Profiler] Fix Windows 64 bit stack walking #6583
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
the
area:profiler
Execution-Time Benchmarks Report ⏱️Execution-time results for samples comparing the following branches/commits: 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 shown in red. The following thresholds were used for comparing the execution times:
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). gantt
title Execution time (ms) FakeDbCommand (.NET Framework 4.6.2)
dateFormat X
axisFormat %s
todayMarker off
section Baseline
This PR (6583) - mean (69ms) : 66, 73
. : milestone, 69,
master - mean (69ms) : 66, 72
. : milestone, 69,
section CallTarget+Inlining+NGEN
This PR (6583) - mean (982ms) : 956, 1008
. : milestone, 982,
master - mean (985ms) : 961, 1010
. : milestone, 985,
gantt
title Execution time (ms) FakeDbCommand (.NET Core 3.1)
dateFormat X
axisFormat %s
todayMarker off
section Baseline
This PR (6583) - mean (108ms) : 106, 110
. : milestone, 108,
master - mean (109ms) : 106, 111
. : milestone, 109,
section CallTarget+Inlining+NGEN
This PR (6583) - mean (684ms) : 667, 702
. : milestone, 684,
master - mean (684ms) : 667, 701
. : milestone, 684,
gantt
title Execution time (ms) FakeDbCommand (.NET 6)
dateFormat X
axisFormat %s
todayMarker off
section Baseline
This PR (6583) - mean (92ms) : 90, 93
. : milestone, 92,
master - mean (92ms) : 90, 93
. : milestone, 92,
section CallTarget+Inlining+NGEN
This PR (6583) - mean (638ms) : 621, 654
. : milestone, 638,
master - mean (635ms) : 619, 650
. : milestone, 635,
gantt
title Execution time (ms) HttpMessageHandler (.NET Framework 4.6.2)
dateFormat X
axisFormat %s
todayMarker off
section Baseline
This PR (6583) - mean (189ms) : 186, 193
. : milestone, 189,
master - mean (189ms) : 186, 193
. : milestone, 189,
section CallTarget+Inlining+NGEN
This PR (6583) - mean (1,093ms) : 1059, 1128
. : milestone, 1093,
master - mean (1,087ms) : 1062, 1113
. : milestone, 1087,
gantt
title Execution time (ms) HttpMessageHandler (.NET Core 3.1)
dateFormat X
axisFormat %s
todayMarker off
section Baseline
This PR (6583) - mean (276ms) : 271, 281
. : milestone, 276,
master - mean (275ms) : 271, 280
. : milestone, 275,
section CallTarget+Inlining+NGEN
This PR (6583) - mean (873ms) : 844, 901
. : milestone, 873,
master - mean (874ms) : 845, 903
. : milestone, 874,
gantt
title Execution time (ms) HttpMessageHandler (.NET 6)
dateFormat X
axisFormat %s
todayMarker off
section Baseline
This PR (6583) - mean (264ms) : 261, 268
. : milestone, 264,
master - mean (265ms) : 262, 268
. : milestone, 265,
section CallTarget+Inlining+NGEN
This PR (6583) - mean (849ms) : 818, 881
. : milestone, 849,
master - mean (854ms) : 823, 884
. : milestone, 854,
|
Datadog ReportBranch report: ✅ 0 Failed, 248670 Passed, 2470 Skipped, 20h 52m 23.58s Total Time |
Benchmarks Report for tracer 🐌Benchmarks for #6583 compared to master:
The following thresholds were used for comparing the benchmark speeds:
Allocation changes below 0.5% are ignored. Benchmark detailsBenchmarks.Trace.ActivityBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.AgentWriterBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.AspNetCoreBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.DbCommandBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.ElasticsearchBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.GraphQLBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.HttpClientBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.ILoggerBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.Log4netBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.NLogBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.RedisBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.SerilogBenchmark - Same speed ✔️ Same allocations ✔️Raw results
Benchmarks.Trace.SpanBenchmark - Faster 🎉 Same allocations ✔️
|
| Benchmark | base/diff | Base Median (ns) | Diff Median (ns) | Modality |
|---|---|---|---|---|
| Benchmarks.Trace.SpanBenchmark.StartFinishSpan‑net6.0 | 1.147 | 452.77 | 394.85 |
Raw results
| Branch | Method | Toolchain | Mean | StdError | StdDev | Gen 0 | Gen 1 | Gen 2 | Allocated |
|---|---|---|---|---|---|---|---|---|---|
| master | StartFinishSpan |
net6.0 | 452ns | 0.614ns | 2.38ns | 0.00813 | 0 | 0 | 576 B |
| master | StartFinishSpan |
netcoreapp3.1 | 564ns | 0.835ns | 3.01ns | 0.00773 | 0 | 0 | 576 B |
| master | StartFinishSpan |
net472 | 600ns | 1.25ns | 4.84ns | 0.0918 | 0 | 0 | 578 B |
| master | StartFinishScope |
net6.0 | 536ns | 0.73ns | 2.83ns | 0.00984 | 0 | 0 | 696 B |
| master | StartFinishScope |
netcoreapp3.1 | 687ns | 1.67ns | 6.48ns | 0.00963 | 0 | 0 | 696 B |
| master | StartFinishScope |
net472 | 868ns | 1.77ns | 6.84ns | 0.104 | 0 | 0 | 658 B |
| #6583 | StartFinishSpan |
net6.0 | 396ns | 0.754ns | 2.92ns | 0.00814 | 0 | 0 | 576 B |
| #6583 | StartFinishSpan |
netcoreapp3.1 | 590ns | 1.1ns | 4.26ns | 0.0079 | 0 | 0 | 576 B |
| #6583 | StartFinishSpan |
net472 | 625ns | 0.984ns | 3.81ns | 0.0916 | 0 | 0 | 578 B |
| #6583 | StartFinishScope |
net6.0 | 565ns | 0.474ns | 1.84ns | 0.00988 | 0 | 0 | 696 B |
| #6583 | StartFinishScope |
netcoreapp3.1 | 698ns | 1.57ns | 6.07ns | 0.00944 | 0 | 0 | 696 B |
| #6583 | StartFinishScope |
net472 | 802ns | 1.84ns | 7.13ns | 0.104 | 0 | 0 | 658 B |
Benchmarks.Trace.TraceAnnotationsBenchmark - Slower ⚠️ Same allocations ✔️
Slower ⚠️ in #6583
Benchmark
diff/base
Base Median (ns)
Diff Median (ns)
Modality
Benchmarks.Trace.TraceAnnotationsBenchmark.RunOnMethodBegin‑netcoreapp3.1
1.187
851.90
1,010.80
| Benchmark | diff/base | Base Median (ns) | Diff Median (ns) | Modality |
|---|---|---|---|---|
| Benchmarks.Trace.TraceAnnotationsBenchmark.RunOnMethodBegin‑netcoreapp3.1 | 1.187 | 851.90 | 1,010.80 |
Raw results
| Branch | Method | Toolchain | Mean | StdError | StdDev | Gen 0 | Gen 1 | Gen 2 | Allocated |
|---|---|---|---|---|---|---|---|---|---|
| master | RunOnMethodBegin |
net6.0 | 626ns | 0.918ns | 3.56ns | 0.00978 | 0 | 0 | 696 B |
| master | RunOnMethodBegin |
netcoreapp3.1 | 853ns | 1.3ns | 5.02ns | 0.00942 | 0 | 0 | 696 B |
| master | RunOnMethodBegin |
net472 | 1.02μs | 2ns | 7.73ns | 0.104 | 0 | 0 | 658 B |
| #6583 | RunOnMethodBegin |
net6.0 | 640ns | 1.1ns | 4.11ns | 0.00993 | 0 | 0 | 696 B |
| #6583 | RunOnMethodBegin |
netcoreapp3.1 | 1.01μs | 1.62ns | 5.61ns | 0.00957 | 0 | 0 | 696 B |
| #6583 | RunOnMethodBegin |
net472 | 1.04μs | 2.41ns | 9.33ns | 0.104 | 0 | 0 | 658 B |
kevingosse
approved these changes
Jan 22, 2025
andrewlock
pushed a commit
that referenced
this pull request
Jan 28, 2025
## Summary of changes
Fix Windows 64 bit stack walking code
## Reason for change
On Windows, 64 bit stack walking failed (maybe after a Visual Studio
update). After investigating, it was due to fact that the execution
context was retrieved in a function that was inlined before. Since this
context is then used in the same method to iterate on different frames,
then the stack should not be updated (i.e. not returning from a function
call).
The existing code should have always failed but a previous version of
the compiler probably decided to inline it. And this is no more the case
for VS 17.12.
## Implementation details
Move the context retrieval code in the same function that walk the stack
## Test coverage
Already covered in all providers that walk the stack
## Other details
<!-- Fixes #{issue} -->
<!-- ⚠️ Note: where possible, please obtain 2 approvals prior to
merging. Unless CODEOWNERS specifies otherwise, for external teams it is
typically best to have one review from a team member, and one review
from apm-dotnet. Trivial changes do not require 2 reviews. -->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary of changes
Fix Windows 64 bit stack walking code
Reason for change
On Windows, 64 bit stack walking failed (maybe after a Visual Studio update). After investigating, it was due to fact that the execution context was retrieved in a function that was inlined before. Since this context is then used in the same method to iterate on different frames, then the stack should not be updated (i.e. not returning from a function call).
The existing code should have always failed but a previous version of the compiler probably decided to inline it. And this is no more the case for VS 17.12.
Implementation details
Move the context retrieval code in the same function that walk the stack
Test coverage
Already covered in all providers that walk the stack
Other details