[Benchmarks] Migrate Windows throughput tests #6785

faydef · 2025-03-20T13:31:07Z

Summary of changes

This PR enables running the Windows based throughput tests through the Benchmarking platform on Gitlab.
The tests are setup to run:

On commit to the master branch
On schedule if BENCHMARK_RUN is set to "true" for the scheduled pipeline.
On manual trigger (keep in mind that it requires build artifacts from the Azure Pipeline)

The results can be checked on the following dashboard (please check the different views as there is a specific view for windows)

Reason for change

The throughput tests previously running on AzDo have been decommissioned.

Implementation details

Additional notes:

datadog-datadog-prod-us1 · 2025-03-20T13:52:59Z

Datadog Report

Branch report: fayssal/windows-throughput-tests-migration
Commit report: e0005e4
Test service: dd-trace-dotnet

✅ 0 Failed, 237053 Passed, 1704 Skipped, 15h 18m 32.1s Total Time

andrewlock · 2025-03-20T14:06:28Z

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 (6785) - mean (70ms)  : 68, 73
     .   : milestone, 70,
    master - mean (69ms)  : 67, 72
     .   : milestone, 69,

    section CallTarget+Inlining+NGEN
    This PR (6785) - mean (1,009ms)  : 988, 1031
     .   : milestone, 1009,
    master - mean (1,006ms)  : 985, 1026
     .   : milestone, 1006,

gantt
    title Execution time (ms) FakeDbCommand (.NET Core 3.1) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (6785) - mean (108ms)  : 103, 112
     .   : milestone, 108,
    master - mean (103ms)  : 101, 105
     .   : milestone, 103,

    section CallTarget+Inlining+NGEN
    This PR (6785) - mean (702ms)  : 681, 723
     .   : milestone, 702,
    master - mean (687ms)  : 667, 708
     .   : milestone, 687,

gantt
    title Execution time (ms) FakeDbCommand (.NET 6) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (6785) - mean (92ms)  : 88, 95
     .   : milestone, 92,
    master - mean (90ms)  : 88, 92
     .   : milestone, 90,

    section CallTarget+Inlining+NGEN
    This PR (6785) - mean (648ms)  : 630, 666
     .   : milestone, 648,
    master - mean (645ms)  : 626, 664
     .   : milestone, 645,

gantt
    title Execution time (ms) HttpMessageHandler (.NET Framework 4.6.2) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (6785) - mean (190ms)  : 186, 194
     .   : milestone, 190,
    master - mean (191ms)  : 184, 197
     .   : milestone, 191,

    section CallTarget+Inlining+NGEN
    This PR (6785) - mean (1,104ms)  : 1081, 1128
     .   : milestone, 1104,
    master - mean (1,110ms)  : 1079, 1141
     .   : milestone, 1110,

gantt
    title Execution time (ms) HttpMessageHandler (.NET Core 3.1) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (6785) - mean (269ms)  : 265, 272
     .   : milestone, 269,
    master - mean (269ms)  : 265, 273
     .   : milestone, 269,

    section CallTarget+Inlining+NGEN
    This PR (6785) - mean (871ms)  : 843, 899
     .   : milestone, 871,
    master - mean (872ms)  : 847, 898
     .   : milestone, 872,

gantt
    title Execution time (ms) HttpMessageHandler (.NET 6) 
    dateFormat  X
    axisFormat %s
    todayMarker off
    section Baseline
    This PR (6785) - mean (262ms)  : 259, 264
     .   : milestone, 262,
    master - mean (262ms)  : 258, 266
     .   : milestone, 262,

    section CallTarget+Inlining+NGEN
    This PR (6785) - mean (854ms)  : 822, 885
     .   : milestone, 854,
    master - mean (858ms)  : 824, 892
     .   : milestone, 858,

andrewlock · 2025-03-20T14:41:57Z

Benchmarks Report for tracer 🐌

Benchmarks for #6785 compared to master:

2 benchmarks are faster, with geometric mean 1.127
1 benchmarks have more 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	7.96μs	44.7ns	313ns	0.0202	0.00809	0	5.62 KB
master	`StartStopWithChild`	netcoreapp3.1	10.1μs	55.5ns	356ns	0.024	0.0144	0.00479	5.8 KB
master	`StartStopWithChild`	net472	16.2μs	56.4ns	219ns	1.04	0.299	0.0968	6.21 KB
#6785	`StartStopWithChild`	net6.0	7.89μs	42.4ns	220ns	0.0152	0.00761	0	5.61 KB
#6785	`StartStopWithChild`	netcoreapp3.1	10.2μs	56.9ns	378ns	0.0204	0.0102	0	5.8 KB
#6785	`StartStopWithChild`	net472	16.4μs	31.3ns	113ns	1.04	0.305	0.0962	6.21 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`WriteAndFlushEnrichedTraces`	net6.0	499μs	260ns	937ns	0	2.7 KB
master	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	649μs	400ns	1.55μs	0	2.7 KB
master	`WriteAndFlushEnrichedTraces`	net472	843μs	573ns	2.22μs	0.419	3.3 KB
#6785	`WriteAndFlushEnrichedTraces`	net6.0	496μs	697ns	2.61μs	0	2.7 KB
#6785	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	661μs	875ns	3.39μs	0	2.7 KB
#6785	`WriteAndFlushEnrichedTraces`	net472	837μs	658ns	2.46μs	0.417	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	130μs	578ns	2.24μs	0.198	14.47 KB
master	`SendRequest`	netcoreapp3.1	150μs	234ns	907ns	0.223	17.27 KB
master	`SendRequest`	net472	0.000986ns	0.000254ns	0.000949ns	0	0 b
#6785	`SendRequest`	net6.0	132μs	484ns	1.87μs	0.135	14.47 KB
#6785	`SendRequest`	netcoreapp3.1	145μs	428ns	1.66μs	0.211	17.27 KB
#6785	`SendRequest`	net472	0ns	0ns	0ns	0	0 b

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

More allocations ⚠️ in #6785

Benchmark	Base Allocated	Diff Allocated	Change	Change %
Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark.WriteAndFlushEnrichedTraces‑netcoreapp3.1	41.62 KB	41.86 KB	235 B	0.56%

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Gen 1	Gen 2	Allocated
master	`WriteAndFlushEnrichedTraces`	net6.0	570μs	2.74μs	11μs	0.568	0	0	41.68 KB
master	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	680μs	3.77μs	24.7μs	0.347	0	0	41.62 KB
master	`WriteAndFlushEnrichedTraces`	net472	851μs	4.17μs	17.7μs	8.22	2.47	0.411	53.32 KB
#6785	`WriteAndFlushEnrichedTraces`	net6.0	592μs	3.28μs	19.4μs	0.581	0	0	41.76 KB
#6785	`WriteAndFlushEnrichedTraces`	netcoreapp3.1	685μs	4.45μs	43.8μs	0.353	0	0	41.86 KB
#6785	`WriteAndFlushEnrichedTraces`	net472	891μs	4.08μs	16.3μs	8.42	2.66	0.443	53.35 KB

Benchmarks.Trace.DbCommandBenchmark - Faster 🎉 Same allocations ✔️

Faster 🎉 in #6785

Benchmark	base/diff	Base Median (ns)	Diff Median (ns)	Modality
Benchmarks.Trace.DbCommandBenchmark.ExecuteNonQuery‑net6.0	1.124	1,426.92	1,268.95

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Gen 1	Allocated
master	`ExecuteNonQuery`	net6.0	1.43μs	1.54ns	5.95ns	0.0142	0	1.02 KB
master	`ExecuteNonQuery`	netcoreapp3.1	1.77μs	2.3ns	8.91ns	0.0133	0	1.02 KB
master	`ExecuteNonQuery`	net472	2.1μs	1.62ns	5.85ns	0.156	0.00107	987 B
#6785	`ExecuteNonQuery`	net6.0	1.26μs	3.64ns	14.1ns	0.014	0	1.02 KB
#6785	`ExecuteNonQuery`	netcoreapp3.1	1.84μs	2ns	7.74ns	0.0138	0	1.02 KB
#6785	`ExecuteNonQuery`	net472	2.14μs	5.63ns	21.8ns	0.156	0.00105	987 B

Benchmarks.Trace.ElasticsearchBenchmark - Faster 🎉 Same allocations ✔️

Faster 🎉 in #6785

Benchmark	base/diff	Base Median (ns)	Diff Median (ns)	Modality
Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearchAsync‑net6.0	1.130	1,395.38	1,234.56

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`CallElasticsearch`	net6.0	1.25μs	0.455ns	1.76ns	0.0138	976 B
master	`CallElasticsearch`	netcoreapp3.1	1.58μs	4.69ns	18.2ns	0.0134	976 B
master	`CallElasticsearch`	net472	2.73μs	1.3ns	4.87ns	0.157	995 B
master	`CallElasticsearchAsync`	net6.0	1.4μs	0.516ns	2ns	0.0133	952 B
master	`CallElasticsearchAsync`	netcoreapp3.1	1.62μs	1.27ns	4.58ns	0.0139	1.02 KB
master	`CallElasticsearchAsync`	net472	2.68μs	1.27ns	4.92ns	0.167	1.05 KB
#6785	`CallElasticsearch`	net6.0	1.18μs	0.396ns	1.43ns	0.0136	976 B
#6785	`CallElasticsearch`	netcoreapp3.1	1.59μs	1.35ns	5.23ns	0.0129	976 B
#6785	`CallElasticsearch`	net472	2.55μs	1.89ns	7.31ns	0.157	995 B
#6785	`CallElasticsearchAsync`	net6.0	1.23μs	0.677ns	2.53ns	0.0135	952 B
#6785	`CallElasticsearchAsync`	netcoreapp3.1	1.64μs	0.77ns	2.88ns	0.014	1.02 KB
#6785	`CallElasticsearchAsync`	net472	2.64μs	1.51ns	5.85ns	0.166	1.05 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`ExecuteAsync`	net6.0	1.35μs	1.29ns	4.83ns	0.0134	952 B
master	`ExecuteAsync`	netcoreapp3.1	1.67μs	0.933ns	3.36ns	0.0125	952 B
master	`ExecuteAsync`	net472	1.76μs	0.378ns	1.31ns	0.145	915 B
#6785	`ExecuteAsync`	net6.0	1.24μs	0.459ns	1.72ns	0.013	952 B
#6785	`ExecuteAsync`	netcoreapp3.1	1.56μs	1.04ns	4.02ns	0.0125	952 B
#6785	`ExecuteAsync`	net472	1.72μs	0.87ns	3.37ns	0.145	915 B

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`SendAsync`	net6.0	4.41μs	1.19ns	4.6ns	0.033	2.31 KB
master	`SendAsync`	netcoreapp3.1	5.34μs	2.59ns	10ns	0.0376	2.85 KB
master	`SendAsync`	net472	7.51μs	1.99ns	7.45ns	0.495	3.12 KB
#6785	`SendAsync`	net6.0	4.45μs	1.25ns	4.86ns	0.0311	2.31 KB
#6785	`SendAsync`	netcoreapp3.1	5.31μs	2.47ns	9.57ns	0.0375	2.85 KB
#6785	`SendAsync`	net472	7.54μs	1.85ns	7.16ns	0.493	3.12 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`EnrichedLog`	net6.0	1.62μs	1.11ns	4.16ns	0.0233	1.69 KB
master	`EnrichedLog`	netcoreapp3.1	2.34μs	0.923ns	3.33ns	0.0223	1.69 KB
master	`EnrichedLog`	net472	2.67μs	1.21ns	4.52ns	0.258	1.62 KB
#6785	`EnrichedLog`	net6.0	1.59μs	0.7ns	2.71ns	0.0239	1.69 KB
#6785	`EnrichedLog`	netcoreapp3.1	2.33μs	0.764ns	2.96ns	0.0224	1.69 KB
#6785	`EnrichedLog`	net472	2.57μs	1.2ns	4.65ns	0.258	1.62 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	164ns	636ns	0	0	4.3 KB
master	`EnrichedLog`	netcoreapp3.1	118μs	267ns	1.04μs	0	0	4.3 KB
master	`EnrichedLog`	net472	151μs	135ns	523ns	0.679	0.226	4.49 KB
#6785	`EnrichedLog`	net6.0	115μs	82.3ns	308ns	0	0	4.3 KB
#6785	`EnrichedLog`	netcoreapp3.1	118μs	181ns	702ns	0.0587	0	4.3 KB
#6785	`EnrichedLog`	net472	151μs	159ns	615ns	0.676	0.225	4.49 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`EnrichedLog`	net6.0	3.07μs	1.06ns	3.67ns	0.0318	2.25 KB
master	`EnrichedLog`	netcoreapp3.1	4.19μs	3.78ns	14.6ns	0.0293	2.25 KB
master	`EnrichedLog`	net472	4.94μs	2.56ns	9.93ns	0.328	2.07 KB
#6785	`EnrichedLog`	net6.0	2.95μs	0.769ns	2.77ns	0.0311	2.25 KB
#6785	`EnrichedLog`	netcoreapp3.1	4.29μs	0.878ns	3.17ns	0.03	2.25 KB
#6785	`EnrichedLog`	net472	4.81μs	2.05ns	7.93ns	0.327	2.07 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`SendReceive`	net6.0	1.34μs	1.76ns	6.84ns	0.0161	1.14 KB
master	`SendReceive`	netcoreapp3.1	1.79μs	0.716ns	2.77ns	0.0151	1.14 KB
master	`SendReceive`	net472	2.08μs	1.31ns	4.88ns	0.184	1.16 KB
#6785	`SendReceive`	net6.0	1.33μs	0.291ns	1.05ns	0.0159	1.14 KB
#6785	`SendReceive`	netcoreapp3.1	1.78μs	1.52ns	5.88ns	0.0153	1.14 KB
#6785	`SendReceive`	net472	2.11μs	1.85ns	6.94ns	0.183	1.16 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`EnrichedLog`	net6.0	2.67μs	0.706ns	2.64ns	0.0226	1.62 KB
master	`EnrichedLog`	netcoreapp3.1	3.96μs	1.49ns	5.75ns	0.0218	1.67 KB
master	`EnrichedLog`	net472	4.37μs	5.01ns	19.4ns	0.328	2.07 KB
#6785	`EnrichedLog`	net6.0	2.89μs	2.28ns	8.85ns	0.023	1.62 KB
#6785	`EnrichedLog`	netcoreapp3.1	4.11μs	1.15ns	4.45ns	0.0225	1.67 KB
#6785	`EnrichedLog`	net472	4.22μs	1.14ns	4.27ns	0.327	2.07 KB

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`StartFinishSpan`	net6.0	429ns	0.18ns	0.673ns	0.00814	576 B
master	`StartFinishSpan`	netcoreapp3.1	554ns	0.301ns	1.17ns	0.0078	576 B
master	`StartFinishSpan`	net472	642ns	0.2ns	0.748ns	0.0917	578 B
master	`StartFinishScope`	net6.0	494ns	0.122ns	0.473ns	0.00981	696 B
master	`StartFinishScope`	netcoreapp3.1	718ns	0.573ns	2.22ns	0.00921	696 B
master	`StartFinishScope`	net472	815ns	0.307ns	1.19ns	0.105	658 B
#6785	`StartFinishSpan`	net6.0	393ns	0.117ns	0.437ns	0.00802	576 B
#6785	`StartFinishSpan`	netcoreapp3.1	543ns	0.253ns	0.981ns	0.00786	576 B
#6785	`StartFinishSpan`	net472	670ns	0.811ns	3.14ns	0.0918	578 B
#6785	`StartFinishScope`	net6.0	523ns	0.173ns	0.647ns	0.00983	696 B
#6785	`StartFinishScope`	netcoreapp3.1	664ns	0.334ns	1.25ns	0.00937	696 B
#6785	`StartFinishScope`	net472	894ns	0.544ns	2.11ns	0.104	658 B

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

Raw results

Branch	Method	Toolchain	Mean	StdError	StdDev	Gen 0	Allocated
master	`RunOnMethodBegin`	net6.0	619ns	1.84ns	7.12ns	0.00988	696 B
master	`RunOnMethodBegin`	netcoreapp3.1	956ns	0.501ns	1.94ns	0.0092	696 B
master	`RunOnMethodBegin`	net472	1.1μs	0.272ns	0.98ns	0.104	658 B
#6785	`RunOnMethodBegin`	net6.0	682ns	1.66ns	6.42ns	0.00962	696 B
#6785	`RunOnMethodBegin`	netcoreapp3.1	896ns	0.43ns	1.67ns	0.00942	696 B
#6785	`RunOnMethodBegin`	net472	1.08μs	0.315ns	1.22ns	0.105	658 B

andrewlock

IT looks like they're working, so LGTM! Thanks 😄

ddyurchenko · 2025-03-21T13:54:50Z

.gitlab/benchmarks/macrobenchmarks.yml

+    - export BP_INFRA_KEY_PAIR_NAME=$(cat ~/.aws/key-pair-name.txt)
+    - export BP_INFRA_KEY_PAIR_PRIVATE_KEY_PATH=~/.aws/key-pair-private-key.pem
+    - git clone --branch fayssal/migrate-macros-dotnet https://gitlab-ci-token:${CI_JOB_TOKEN}@gitlab.ddbuild.io/DataDog/benchmarking-platform platform
+    - ./platform/pass-artifatcs-to-windows.sh


./platform/pass-artifatcs-to-windows.sh

Typo in script name.

Thank you, actually it's a typo in the name of the file downstream itself 😅 (hence why the tests are successful), I'll change the name of the file and thus the name in the script!

ddyurchenko · 2025-03-21T14:30:06Z

.gitlab/benchmarks/macrobenchmarks.yml

+  image: registry.ddbuild.io/images/benchmarking-platform-tools-ubuntu:dotnet-tests
+
+  script:
+    - export DD_API_KEY=$(aws ssm get-parameter --region us-east-1 --name ci.$CI_PROJECT_NAME.dd_api_key --with-decryption --query "Parameter.Value" --out text)


Hey, do you think we can encapsulate it a lil bit better? I would prefer to have a single script call, similar to what we have in https://github.com/DataDog/dd-trace-dotnet/blob/master/.gitlab/benchmarks/macrobenchmarks.yml#L49, SSM details should really belong inside benchmarking-platform repo (and in long term, we should move it to bp-runner, as this seems to be a code used universally for Windows runners).

Everything else looks good, we have results in DD dashboard! 🎉
We will need to do some audit of results, it is 4x faster than Linux? Seems interesting!

it is 4x faster than Linux? Seems interesting

Are these running on the same spec machines?! Because that seems very suspect to me😅 For comparison, our previous crank-based implementation showed that Windows was ~10% slower than Linux

Yep, same spec, m5.metal. Thank you for confirming Andrew, we definitely need to look into it!

Also, thanks for sharing, that is really lovely dashboard! 🙌 💜

Interesting 🤔 , is cross-os comparison one of the use-cases?

Are these running on the same spec machines?!

Same spec machines yes, although on windows we assign a couple more cpus to the throughput server (anticipating windows being less efficient) .
Now that I think about it, I will revert back to having the same setup across os to ensure we can have the option if wanted!

Here - https://ddstaging.datadoghq.com/dashboard/rgu-p7u-5fq?fromUser=false&refresh_mode=sliding&tpl_var_bp_branch%5B0%5D=fayssal%2Fmigrate-throughput-tests-windows&from_ts=1739975186532&to_ts=1742567186532&live=true

I think we should address it before giving green light to a PR.

although on windows we assign a couple more cpus to the throughput server (anticipating windows being less efficient) .

That must be it.
But it won't hurt to check if instrumentation is applied. Overhead numbers are super small.

ddyurchenko · 2025-03-21T17:27:15Z

.gitlab/benchmarks/macrobenchmarks.yml

+.benchmarks-win:
+  stage: benchmarks-win
+  needs: ["check_azure_pipeline"]
+  tags: ["runner:docker"]


I think runner: docker is deprecated nowadays and we should use arch:amd64, unless there is really a compelling reason to keep it.

add jobs to trigger macrobenchmarks from dd-trace-dotnet repo

e9b73e8

remove duplicate key fetching

24f339b

faydef changed the title ~~add jobs to trigger macrobenchmarks from dd-trace-dotnet repo~~ [Benchmarks] Migrate Windows throughput tests Mar 21, 2025

faydef marked this pull request as ready for review March 21, 2025 08:37

faydef requested a review from a team as a code owner March 21, 2025 08:37

faydef requested a review from ddyurchenko March 21, 2025 08:38

andrewlock approved these changes Mar 21, 2025

View reviewed changes

ddyurchenko reviewed Mar 21, 2025

View reviewed changes

faydef added 2 commits March 21, 2025 16:07

fix: align woth typo fix for file name

f2934bd

use a seperate stage for windows benchmarks

3cc0796

ddyurchenko reviewed Mar 21, 2025

View reviewed changes

faydef added 4 commits March 24, 2025 09:14

Change runner tags

c156c18

refactor: Encapsulate the CI commands in a script

0ce90c7

refactor: Pass down rates through the .env.example file

a2516d8

wip:test on master to expedite tests

ec820c3

faydef force-pushed the fayssal/windows-throughput-tests-migration branch from 8d226c3 to ec820c3 Compare March 24, 2025 09:03

faydef added 2 commits March 24, 2025 10:08

fix: allow arm benchmarks to run on success

924810f

refactor: set k6 env vars through CI

e0005e4

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Benchmarks] Migrate Windows throughput tests #6785

[Benchmarks] Migrate Windows throughput tests #6785

faydef commented Mar 20, 2025 •

edited

Loading

datadog-datadog-prod-us1 bot commented Mar 20, 2025 •

edited

Loading

andrewlock commented Mar 20, 2025 •

edited

Loading

andrewlock commented Mar 20, 2025 •

edited

Loading

Raw results

Raw results

Raw results

More allocations ⚠️ in #6785

Raw results

Faster 🎉 in #6785

Raw results

Faster 🎉 in #6785

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

andrewlock left a comment

ddyurchenko Mar 21, 2025

faydef Mar 21, 2025

ddyurchenko Mar 21, 2025

ddyurchenko Mar 21, 2025

andrewlock Mar 21, 2025

ddyurchenko Mar 21, 2025

faydef Mar 21, 2025 •

edited

Loading

ddyurchenko Mar 21, 2025

ddyurchenko Mar 21, 2025

ddyurchenko Mar 21, 2025

[Benchmarks] Migrate Windows throughput tests #6785

Are you sure you want to change the base?

[Benchmarks] Migrate Windows throughput tests #6785

Conversation

faydef commented Mar 20, 2025 • edited Loading

Summary of changes

Reason for change

Implementation details

Additional notes:

datadog-datadog-prod-us1 bot commented Mar 20, 2025 • edited Loading

Datadog Report

andrewlock commented Mar 20, 2025 • edited Loading

Execution-Time Benchmarks Report ⏱️

andrewlock commented Mar 20, 2025 • edited Loading

Benchmarks Report for tracer 🐌

Benchmark details

Raw results

Raw results

Raw results

More allocations ⚠️ in #6785

Raw results

Faster 🎉 in #6785

Raw results

Faster 🎉 in #6785

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

Raw results

andrewlock left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

faydef Mar 21, 2025 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

faydef commented Mar 20, 2025 •

edited

Loading

datadog-datadog-prod-us1 bot commented Mar 20, 2025 •

edited

Loading

andrewlock commented Mar 20, 2025 •

edited

Loading

andrewlock commented Mar 20, 2025 •

edited

Loading

faydef Mar 21, 2025 •

edited

Loading