[Profiler] Use a homemade implementation of linked-list #5284

gleocadie · 2024-03-07T10:41:48Z

Summary of changes

Homemade implementation of a linked list.

Reason for change

We plan to use for some (maybe all) of our profilers a ring-buffer-based allocator. This allocator may return nullptr when there is not enough room.

std::list does not support allocators which returns nullptr. So we need our own implementation which allows nullptr to be returned.
In the upper layer, this will measure (metrics, logs...)

Implementation details

new LinkedList class which takes a memory_resource as ctor parameter. The default memory_resource is new/delete (same behavior as today with a std::list). This class is move-only to simplify it's implementation (if there is a copy, we do not want to copy all the elements)
Replace the usage of std::list in RawSamples

Test coverage

Add unit tests
Integration tests should still work.

Other details

datadog-ddstaging · 2024-03-07T11:05:38Z

Datadog Report

Branch report: gleocadie/use-homemade-implementation-of-linked-list
Commit report: 9397f9a
Test service: dd-trace-dotnet

✅ 0 Failed, 329328 Passed, 1861 Skipped, 35m 31.12s Wall Time
❄️ 1 New Flaky

New Flaky Tests (1)

NoTraceContextAttachedIfFeatureDeactivated - Datadog.Profiler.IntegrationTests.CodeHotspot.CodeHotspotTest - Last Failure
Expand for error
```
 Exit code of "catchsegv" should be 0 instead of 139 (= 0x8B)
 Expected: True
 Actual:   False
```

andrewlock · 2024-03-07T11:42:19Z

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:

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).

gantt
    title Execution time (ms) FakeDbCommand (.NET Framework 4.6.2) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (5284) - mean (74ms)  : 65, 84
     .   : milestone, 74,
    master - mean (73ms)  : 65, 81
     .   : milestone, 73,

    section CallTarget+Inlining+NGEN
    This PR (5284) - mean (1,011ms)  : 989, 1033
     .   : milestone, 1011,
    master - mean (1,005ms)  : 977, 1033
     .   : milestone, 1005,

gantt
    title Execution time (ms) FakeDbCommand (.NET Core 3.1) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (5284) - mean (111ms)  : 108, 114
     .   : milestone, 111,
    master - mean (110ms)  : 107, 114
     .   : milestone, 110,

    section CallTarget+Inlining+NGEN
    This PR (5284) - mean (725ms)  : 700, 749
     .   : milestone, 725,
    master - mean (725ms)  : 703, 748
     .   : milestone, 725,

gantt
    title Execution time (ms) FakeDbCommand (.NET 6) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (5284) - mean (95ms)  : 92, 98
     .   : milestone, 95,
    master - mean (93ms)  : 91, 96
     .   : milestone, 93,

    section CallTarget+Inlining+NGEN
    This PR (5284) - mean (680ms)  : 649, 711
     .   : milestone, 680,
    master - mean (675ms)  : 652, 698
     .   : milestone, 675,

gantt
    title Execution time (ms) HttpMessageHandler (.NET Framework 4.6.2) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (5284) - mean (188ms)  : 185, 191
     .   : milestone, 188,
    master - mean (188ms)  : 185, 192
     .   : milestone, 188,

    section CallTarget+Inlining+NGEN
    This PR (5284) - mean (1,081ms)  : 1057, 1106
     .   : milestone, 1081,
    master - mean (1,075ms)  : 1047, 1104
     .   : milestone, 1075,

gantt
    title Execution time (ms) HttpMessageHandler (.NET Core 3.1) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (5284) - mean (272ms)  : 268, 276
     .   : milestone, 272,
    master - mean (272ms)  : 268, 276
     .   : milestone, 272,

    section CallTarget+Inlining+NGEN
    This PR (5284) - mean (881ms)  : 858, 903
     .   : milestone, 881,
    master - mean (883ms)  : 856, 909
     .   : milestone, 883,

gantt
    title Execution time (ms) HttpMessageHandler (.NET 6) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (5284) - mean (261ms)  : 257, 266
     .   : milestone, 261,
    master - mean (261ms)  : 257, 265
     .   : milestone, 261,

    section CallTarget+Inlining+NGEN
    This PR (5284) - mean (858ms)  : 835, 880
     .   : milestone, 858,
    master - mean (855ms)  : 830, 880
     .   : milestone, 855,

andrewlock · 2024-03-08T06:59:53Z

Throughput/Crank Report:zap:

Throughput results for AspNetCoreSimpleController comparing the following branches/commits:

Cases where throughput results for the PR are worse than latest master (5% drop or greater), results are shown in red.

Note that these results are based on a single point-in-time result for each branch. For full results, see one of the many, many dashboards!

gantt
    title Throughput Linux x64 (Total requests) 
    dateFormat  X
    axisFormat %s
    section Baseline
    This PR (5284) (11.219M)   : 0, 11218526
    master (11.301M)   : 0, 11301171
    benchmarks/2.9.0 (10.912M)   : 0, 10912209

    section Automatic
    This PR (5284) (7.767M)   : 0, 7766653
    master (7.786M)   : 0, 7786387
    benchmarks/2.9.0 (8.150M)   : 0, 8149943

    section Trace stats
    This PR (5284) (8.058M)   : 0, 8058458
    master (8.162M)   : 0, 8161989

    section Manual
    This PR (5284) (9.844M)   : 0, 9843651
    master (9.926M)   : 0, 9926297

    section Manual + Automatic
    This PR (5284) (7.316M)   : 0, 7315638
    master (7.412M)   : 0, 7411648

    section Version Conflict
    This PR (5284) (6.604M)   : 0, 6603824
    master (6.730M)   : 0, 6730224

gantt
    title Throughput Linux arm64 (Total requests) 
    dateFormat  X
    axisFormat %s
    section Baseline
    This PR (5284) (9.412M)   : 0, 9412460
    master (9.529M)   : 0, 9529282
    benchmarks/2.9.0 (9.446M)   : 0, 9446328

    section Automatic
    This PR (5284) (6.671M)   : 0, 6670905
    master (6.506M)   : 0, 6505611

    section Trace stats
    This PR (5284) (6.795M)   : 0, 6795071
    master (6.940M)   : 0, 6940301

    section Manual
    This PR (5284) (8.406M)   : 0, 8405929
    master (8.383M)   : 0, 8383218

    section Manual + Automatic
    This PR (5284) (6.204M)   : 0, 6204136
    master (6.263M)   : 0, 6262794

    section Version Conflict
    This PR (5284) (5.771M)   : 0, 5770660
    master (5.698M)   : 0, 5698114

gantt
    title Throughput Windows x64 (Total requests) 
    dateFormat  X
    axisFormat %s
    section Baseline
    This PR (5284) (10.482M)   : 0, 10481888
    master (10.221M)   : 0, 10221490
    benchmarks/2.9.0 (10.227M)   : 0, 10226734

    section Automatic
    This PR (5284) (7.315M)   : 0, 7314813
    master (7.341M)   : 0, 7340809
    benchmarks/2.9.0 (7.735M)   : 0, 7734705

    section Trace stats
    This PR (5284) (7.653M)   : 0, 7652770
    master (7.697M)   : 0, 7697428

    section Manual
    This PR (5284) (9.254M)   : 0, 9253805
    master (9.139M)   : 0, 9138836

    section Manual + Automatic
    This PR (5284) (7.040M)   : 0, 7040073
    master (7.059M)   : 0, 7058587

    section Version Conflict
    This PR (5284) (6.401M)   : 0, 6400614
    master (6.504M)   : 0, 6503694

gantt
    title Throughput Linux x64 (ASM) (Total requests) 
    dateFormat  X
    axisFormat %s
    section Baseline
    master (7.461M)   : 0, 7461396
    benchmarks/2.9.0 (7.826M)   : 0, 7826159

    section No attack
    master (1.854M)   : 0, 1853890
    benchmarks/2.9.0 (3.248M)   : 0, 3247998

    section Attack
    master (1.450M)   : 0, 1449724
    benchmarks/2.9.0 (2.477M)   : 0, 2477217

    section Blocking
    master (3.161M)   : 0, 3160542

    section IAST default
    master (6.464M)   : 0, 6464188

    section IAST full
    master (5.600M)   : 0, 5600403

    section Base vuln
    master (0.918M)   : 0, 917723

    section IAST vuln
    master (0.859M)   : 0, 859223

chrisnas

LGTM with a couple of comments

profiler/src/ProfilerEngine/Datadog.Profiler.Native/LinkedList.hpp

profiler/test/Datadog.Profiler.Native.Tests/LinkedListTest.cpp

datadog-ddstaging · 2024-03-27T12:24:25Z

Datadog Report

Branch report: gleocadie/use-homemade-implementation-of-linked-list
Commit report: 37d6a43
Test service: dd-trace-dotnet

✅ 0 Failed, 322572 Passed, 1822 Skipped, 54m 17.48s Wall Time

andrewlock · 2024-03-27T13:16:59Z

Benchmarks Report for tracer 🐌

Benchmarks for #5284 compared to master:

1 benchmarks are slower, with geometric mean 1.139
All benchmarks have the same allocations

The following thresholds were used for comparing the benchmark speeds:

Mann–Whitney U test with statistical test for significance of 5%
Only results indicating a difference greater than 10% and 0.3 ns are considered.

Allocation changes below 0.5% are ignored.

Benchmark details

Benchmarks.Trace.ActivityBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Gen 1	Gen 2	Allocated
master	`StartStopWithChild`	net6.0	8.76μs	48.5ns	303ns	0.0218	0.00871	0	7.51 KB
master	`StartStopWithChild`	netcoreapp3.1	10.7μs	58.2ns	324ns	0.0167	0.00557	0	7.6 KB
master	`StartStopWithChild`	net472	16.9μs	61.8ns	239ns	1.34	0.334	0.1	8.06 KB
#5284	`StartStopWithChild`	net6.0	9.52μs	54.8ns	414ns	0.0238	0.00953	0	7.51 KB
#5284	`StartStopWithChild`	netcoreapp3.1	11.2μs	58.5ns	275ns	0.0219	0.00548	0	7.61 KB
#5284	`StartStopWithChild`	net472	17μs	24.3ns	91ns	1.32	0.322	0.102	8.05 KB

Benchmarks.Trace.AgentWriterBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`WriteAndFlushEnrichedTraces`	net6.0	443μs	183ns	686ns	0	2.7 KB
master	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	611μs	85.3ns	296ns	0	2.7 KB
master	`WriteAndFlushEnrichedTraces`	net472	812μs	361ns	1.4μs	0.406	3.3 KB
#5284	`WriteAndFlushEnrichedTraces`	net6.0	456μs	188ns	727ns	0	2.7 KB
#5284	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	613μs	173ns	622ns	0	2.7 KB
#5284	`WriteAndFlushEnrichedTraces`	net472	819μs	377ns	1.46μs	0.406	3.3 KB

Benchmarks.Trace.AspNetCoreBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`SendRequest`	net6.0	170μs	167ns	624ns	0.169	18.33 KB
master	`SendRequest`	netcoreapp3.1	195μs	345ns	1.34μs	0.193	20.49 KB
master	`SendRequest`	net472	0.00128ns	0.000429ns	0.00166ns	0	0 b
#5284	`SendRequest`	net6.0	171μs	139ns	520ns	0.255	18.34 KB
#5284	`SendRequest`	netcoreapp3.1	192μs	254ns	949ns	0.191	20.5 KB
#5284	`SendRequest`	net472	0.000148ns	0.000131ns	0.000474ns	0	0 b

Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Gen 1	Gen 2	Allocated
master	`WriteAndFlushEnrichedTraces`	net6.0	548μs	2.68μs	11.4μs	0.541	0	0	41.65 KB
master	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	645μs	1.53μs	5.91μs	0.326	0	0	41.64 KB
master	`WriteAndFlushEnrichedTraces`	net472	876μs	3.11μs	11.6μs	8.13	2.57	0.428	53.23 KB
#5284	`WriteAndFlushEnrichedTraces`	net6.0	537μs	559ns	2.02μs	0.539	0	0	41.63 KB
#5284	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	641μs	1.53μs	5.94μs	0.319	0	0	41.53 KB
#5284	`WriteAndFlushEnrichedTraces`	net472	861μs	4.37μs	19.1μs	8.13	2.57	0.428	53.24 KB

Benchmarks.Trace.DbCommandBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`ExecuteNonQuery`	net6.0	1.13μs	0.425ns	1.64ns	0.0108	784 B
master	`ExecuteNonQuery`	netcoreapp3.1	1.52μs	3.56ns	13.8ns	0.0106	784 B
master	`ExecuteNonQuery`	net472	1.76μs	0.658ns	2.55ns	0.118	746 B
#5284	`ExecuteNonQuery`	net6.0	1.14μs	0.401ns	1.5ns	0.0108	784 B
#5284	`ExecuteNonQuery`	netcoreapp3.1	1.48μs	0.47ns	1.76ns	0.0104	784 B
#5284	`ExecuteNonQuery`	net472	1.72μs	0.553ns	2.14ns	0.118	746 B

Benchmarks.Trace.ElasticsearchBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`CallElasticsearch`	net6.0	1.24μs	0.356ns	1.33ns	0.0144	1.01 KB
master	`CallElasticsearch`	netcoreapp3.1	1.61μs	0.926ns	3.46ns	0.0138	1.01 KB
master	`CallElasticsearch`	net472	2.47μs	1.83ns	7.09ns	0.161	1.02 KB
master	`CallElasticsearchAsync`	net6.0	1.4μs	1.03ns	3.86ns	0.0141	984 B
master	`CallElasticsearchAsync`	netcoreapp3.1	1.72μs	0.836ns	3.13ns	0.0136	1.06 KB
master	`CallElasticsearchAsync`	net472	2.53μs	1.17ns	4.53ns	0.171	1.08 KB
#5284	`CallElasticsearch`	net6.0	1.24μs	0.906ns	3.51ns	0.0144	1.01 KB
#5284	`CallElasticsearch`	netcoreapp3.1	1.6μs	0.609ns	2.2ns	0.0137	1.01 KB
#5284	`CallElasticsearch`	net472	2.55μs	1.41ns	5.29ns	0.162	1.02 KB
#5284	`CallElasticsearchAsync`	net6.0	1.36μs	1.09ns	4.22ns	0.0135	984 B
#5284	`CallElasticsearchAsync`	netcoreapp3.1	1.75μs	1.02ns	3.69ns	0.0144	1.06 KB
#5284	`CallElasticsearchAsync`	net472	2.69μs	1.97ns	7.63ns	0.17	1.08 KB

Benchmarks.Trace.GraphQLBenchmark - Slower ⚠️ Same allocations ✔️

Slower ⚠️ in #5284

Benchmark	diff/base	Base Median (ns)	Diff Median (ns)	Modality
Benchmarks.Trace.GraphQLBenchmark.ExecuteAsync‑net6.0	1.139	1,258.38	1,433.23

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`ExecuteAsync`	net6.0	1.26μs	1.14ns	4.27ns	0.0128	928 B
master	`ExecuteAsync`	netcoreapp3.1	1.65μs	1.84ns	7.11ns	0.0124	928 B
master	`ExecuteAsync`	net472	1.94μs	1.55ns	6.02ns	0.141	891 B
#5284	`ExecuteAsync`	net6.0	1.43μs	0.561ns	2.1ns	0.0129	928 B
#5284	`ExecuteAsync`	netcoreapp3.1	1.67μs	1.83ns	6.84ns	0.0124	928 B
#5284	`ExecuteAsync`	net472	1.9μs	1.53ns	5.91ns	0.141	891 B

Benchmarks.Trace.HttpClientBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`SendAsync`	net6.0	4.18μs	2.34ns	9.06ns	0.0294	2.16 KB
master	`SendAsync`	netcoreapp3.1	5.06μs	4.51ns	17.5ns	0.0355	2.7 KB
master	`SendAsync`	net472	7.65μs	7.64ns	29.6ns	0.483	3.05 KB
#5284	`SendAsync`	net6.0	4.08μs	2.02ns	7.83ns	0.0287	2.16 KB
#5284	`SendAsync`	netcoreapp3.1	5.08μs	4.28ns	16.6ns	0.0353	2.7 KB
#5284	`SendAsync`	net472	7.74μs	3.91ns	15.1ns	0.483	3.05 KB

Benchmarks.Trace.ILoggerBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`EnrichedLog`	net6.0	1.55μs	0.638ns	2.39ns	0.0232	1.65 KB
master	`EnrichedLog`	netcoreapp3.1	2.3μs	1.22ns	4.55ns	0.0219	1.65 KB
master	`EnrichedLog`	net472	2.74μs	1.28ns	4.81ns	0.249	1.57 KB
#5284	`EnrichedLog`	net6.0	1.58μs	0.355ns	1.23ns	0.0234	1.65 KB
#5284	`EnrichedLog`	netcoreapp3.1	2.32μs	0.959ns	3.71ns	0.0218	1.65 KB
#5284	`EnrichedLog`	net472	2.84μs	1.42ns	5.11ns	0.249	1.57 KB

Benchmarks.Trace.Log4netBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Gen 1	Allocated
master	`EnrichedLog`	net6.0	111μs	87.2ns	338ns	0.0556	0	4.23 KB
master	`EnrichedLog`	netcoreapp3.1	118μs	195ns	755ns	0.0587	0	4.23 KB
master	`EnrichedLog`	net472	147μs	69.3ns	268ns	0.658	0.219	4.41 KB
#5284	`EnrichedLog`	net6.0	111μs	62.2ns	241ns	0.056	0	4.23 KB
#5284	`EnrichedLog`	netcoreapp3.1	117μs	120ns	448ns	0	0	4.23 KB
#5284	`EnrichedLog`	net472	147μs	108ns	403ns	0.66	0.22	4.41 KB

Benchmarks.Trace.NLogBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`EnrichedLog`	net6.0	3.11μs	2.52ns	9.42ns	0.0311	2.21 KB
master	`EnrichedLog`	netcoreapp3.1	3.94μs	3.78ns	14.1ns	0.0294	2.21 KB
master	`EnrichedLog`	net472	4.94μs	4.28ns	16.6ns	0.319	2.02 KB
#5284	`EnrichedLog`	net6.0	2.87μs	1.3ns	5.02ns	0.0316	2.21 KB
#5284	`EnrichedLog`	netcoreapp3.1	4.01μs	2.06ns	7.44ns	0.0305	2.21 KB
#5284	`EnrichedLog`	net472	4.9μs	1.5ns	5.82ns	0.319	2.02 KB

Benchmarks.Trace.RedisBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`SendReceive`	net6.0	1.43μs	3.14ns	11.7ns	0.0163	1.18 KB
master	`SendReceive`	netcoreapp3.1	1.86μs	1.73ns	6.23ns	0.0159	1.18 KB
master	`SendReceive`	net472	2.21μs	2.53ns	9.78ns	0.187	1.18 KB
#5284	`SendReceive`	net6.0	1.44μs	0.687ns	2.57ns	0.0165	1.18 KB
#5284	`SendReceive`	netcoreapp3.1	1.88μs	1.18ns	4.58ns	0.016	1.18 KB
#5284	`SendReceive`	net472	2.29μs	2.51ns	9.07ns	0.187	1.18 KB

Benchmarks.Trace.SerilogBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`EnrichedLog`	net6.0	2.87μs	0.754ns	2.92ns	0.0213	1.55 KB
master	`EnrichedLog`	netcoreapp3.1	3.94μs	2.29ns	8.87ns	0.0218	1.6 KB
master	`EnrichedLog`	net472	4.39μs	3.15ns	12.2ns	0.315	1.99 KB
#5284	`EnrichedLog`	net6.0	2.84μs	1.14ns	4.43ns	0.0215	1.55 KB
#5284	`EnrichedLog`	netcoreapp3.1	3.96μs	1.29ns	4.48ns	0.022	1.6 KB
#5284	`EnrichedLog`	net472	4.42μs	3.33ns	12.9ns	0.315	1.99 KB

Benchmarks.Trace.SpanBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`StartFinishSpan`	net6.0	506ns	0.546ns	2.12ns	0.00775	552 B
master	`StartFinishSpan`	netcoreapp3.1	714ns	1.91ns	7.41ns	0.00745	552 B
master	`StartFinishSpan`	net472	779ns	2.13ns	8.27ns	0.0876	554 B
master	`StartFinishScope`	net6.0	628ns	0.945ns	3.66ns	0.00945	672 B
master	`StartFinishScope`	netcoreapp3.1	868ns	1.64ns	6.36ns	0.00911	672 B
master	`StartFinishScope`	net472	990ns	1.52ns	5.69ns	0.101	634 B
#5284	`StartFinishSpan`	net6.0	485ns	0.853ns	3.3ns	0.00783	552 B
#5284	`StartFinishSpan`	netcoreapp3.1	722ns	0.625ns	2.16ns	0.00755	552 B
#5284	`StartFinishSpan`	net472	806ns	2.01ns	7.77ns	0.088	554 B
#5284	`StartFinishScope`	net6.0	689ns	0.431ns	1.67ns	0.00933	672 B
#5284	`StartFinishScope`	netcoreapp3.1	859ns	2.52ns	9.74ns	0.00924	672 B
#5284	`StartFinishScope`	net472	1.02μs	0.421ns	1.63ns	0.1	634 B

Benchmarks.Trace.TraceAnnotationsBenchmark - Same speed ✔️ Same allocations ✔️

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`RunOnMethodBegin`	net6.0	663ns	0.83ns	3.22ns	0.00962	672 B
master	`RunOnMethodBegin`	netcoreapp3.1	1.02μs	1.54ns	5.77ns	0.0089	672 B
master	`RunOnMethodBegin`	net472	1.11μs	1.83ns	6.84ns	0.1	634 B
#5284	`RunOnMethodBegin`	net6.0	681ns	0.26ns	1.01ns	0.00936	672 B
#5284	`RunOnMethodBegin`	netcoreapp3.1	935ns	0.743ns	2.68ns	0.00874	672 B
#5284	`RunOnMethodBegin`	net472	1.05μs	1.02ns	3.96ns	0.1	634 B

github-actions bot added the area:profiler Issues related to the continous-profiler label Mar 7, 2024

gleocadie force-pushed the gleocadie/use-homemade-implementation-of-linked-list branch 2 times, most recently from 190bd2b to c563272 Compare March 7, 2024 10:51

gleocadie force-pushed the gleocadie/use-homemade-implementation-of-linked-list branch 4 times, most recently from e9d9646 to 5f125a2 Compare March 7, 2024 21:55

gleocadie force-pushed the gleocadie/use-homemade-implementation-of-linked-list branch from 5f125a2 to cd3c579 Compare March 8, 2024 10:48

gleocadie marked this pull request as ready for review March 8, 2024 10:55

gleocadie requested a review from a team as a code owner March 8, 2024 10:55

gleocadie force-pushed the gleocadie/use-homemade-implementation-of-linked-list branch 3 times, most recently from f61e9f6 to 9397f9a Compare March 8, 2024 20:07

chrisnas approved these changes Mar 26, 2024

View reviewed changes

gleocadie added 3 commits March 27, 2024 12:54

Use a homemade implementation of linked-list

92341f3

Improve exception-safety + workaround for ASAN/UBSAN

e944085

Address comment

37d6a43

gleocadie force-pushed the gleocadie/use-homemade-implementation-of-linked-list branch from 9397f9a to 37d6a43 Compare March 27, 2024 11:54

gleocadie merged commit 331a66b into master Mar 27, 2024
60 of 64 checks passed

gleocadie deleted the gleocadie/use-homemade-implementation-of-linked-list branch March 27, 2024 18:51

github-actions bot added this to the vNext milestone Mar 27, 2024

andrewlock modified the milestones: vNext, vNext-v2 Apr 17, 2024

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Profiler] Use a homemade implementation of linked-list #5284

[Profiler] Use a homemade implementation of linked-list #5284

gleocadie commented Mar 7, 2024 •

edited

Loading

datadog-ddstaging bot commented Mar 7, 2024 •

edited

Loading

andrewlock commented Mar 7, 2024 •

edited

Loading

andrewlock commented Mar 8, 2024 •

edited

Loading

chrisnas left a comment

datadog-ddstaging bot commented Mar 27, 2024 •

edited

Loading

andrewlock commented Mar 27, 2024

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Slower ⚠️ in #5284

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

[Profiler] Use a homemade implementation of linked-list #5284

[Profiler] Use a homemade implementation of linked-list #5284

Conversation

gleocadie commented Mar 7, 2024 • edited Loading

Summary of changes

Reason for change

Implementation details

Test coverage

Other details

datadog-ddstaging bot commented Mar 7, 2024 • edited Loading

Datadog Report

New Flaky Tests (1)

andrewlock commented Mar 7, 2024 • edited Loading

Execution-Time Benchmarks Report ⏱️

andrewlock commented Mar 8, 2024 • edited Loading

Throughput/Crank Report:zap:

chrisnas left a comment

Choose a reason for hiding this comment

datadog-ddstaging bot commented Mar 27, 2024 • edited Loading

Datadog Report

andrewlock commented Mar 27, 2024

Benchmarks Report for tracer 🐌

Benchmark details

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Slower ⚠️ in #5284

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

gleocadie commented Mar 7, 2024 •

edited

Loading

datadog-ddstaging bot commented Mar 7, 2024 •

edited

Loading

andrewlock commented Mar 7, 2024 •

edited

Loading

andrewlock commented Mar 8, 2024 •

edited

Loading

datadog-ddstaging bot commented Mar 27, 2024 •

edited

Loading