[APMSP-1013] Add stats exporter

[VianneyRuhlmann]

What does this PR do?

This PR add stats computation in the data pipeline crate by:

• Using a SpanConcentrator to compute stats on received spans in the trace exporter
• Introducing a StatsExporter to send stats on a every time a stats bucket expires
• Dropping spans that are not going to be sampled by the trace agent
• Add support for client-side stats http header
• Update ffi bindings to allow stats computation

Motivation

The support for client side stats will allow using client side stats by default. This will reduce the number of span received by the agent.

Additional Notes

This PR does not allow fetching the list of peer tags from the /info endpoint of the agent.

How to test the change?

Describe here in detail how the change can be validated.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 90.59561% with 60 lines in your changes missing coverage. Please review.

Project coverage is 73.58%. Comparing base (4c7552b) to head (3475380).

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #584      +/-   ##
==========================================
+ Coverage   73.19%   73.58%   +0.39%     
==========================================
  Files         254      255       +1     
  Lines       36312    36941     +629     
==========================================
+ Hits        26578    27183     +605     
- Misses       9734     9758      +24     

Components	Coverage Δ
crashtracker	20.53% <ø> (ø)
datadog-alloc	98.73% <ø> (ø)
data-pipeline	91.65% <90.30%> (+1.48%)	⬆️
data-pipeline-ffi	0.00% <0.00%> (ø)
ddcommon	83.08% <ø> (ø)
ddcommon-ffi	69.52% <ø> (ø)
ddtelemetry	59.10% <ø> (ø)
ipc	83.58% <ø> (ø)
profiling	84.26% <ø> (ø)
profiling-ffi	77.42% <ø> (ø)
serverless	0.00% <ø> (ø)
sidecar	40.10% <ø> (ø)
sidecar-ffi	0.00% <ø> (ø)
spawn-worker	50.36% <ø> (ø)
tinybytes	94.77% <ø> (ø)
trace-mini-agent	72.47% <ø> (ø)
trace-normalization	98.25% <ø> (ø)
trace-obfuscation	95.73% <ø> (ø)
trace-protobuf	77.67% <ø> (ø)
trace-utils	93.41% <100.00%> (-0.13%)	⬇️

[pr-commenter]

Benchmarks

Comparison

Benchmark execution time: 2024-09-20 08:13:26

Comparing candidate commit 3475380 in PR branch vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload with baseline commit 4c7552b in branch main.

Found 1 performance improvements and 2 performance regressions! Performance is the same for 48 metrics, 2 unstable metrics.

scenario:benching deserializing traces from msgpack to their internal representation

• 🟩 execution_time [-53.528ns; -44.490ns] or [-4.297%; -3.571%]

scenario:normalization/normalize_name/normalize_name/good

• 🟥 execution_time [+394.903ns; +418.112ns] or [+2.447%; +2.591%]
• 🟥 throughput [-1567057.934op/s; -1479256.143op/s] or [-2.529%; -2.387%]

Candidate

Candidate benchmark details

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
credit_card/is_card_number/	execution_time	2.415µs	2.416µs ± 0.001µs	2.416µs ± 0.001µs	2.417µs	2.418µs	2.419µs	2.420µs	0.15%	0.949	0.712	0.04%	0.000µs	1	200
credit_card/is_card_number/	throughput	413226110.858op/s	413825096.256op/s ± 160692.978op/s	413865794.021op/s ± 111920.874op/s	413956287.707op/s	414011205.480op/s	414036841.247op/s	414083231.830op/s	0.05%	-0.947	0.705	0.04%	11362.709op/s	1	200
credit_card/is_card_number/ 3782-8224-6310-005	execution_time	111.526µs	115.434µs ± 1.302µs	115.610µs ± 0.887µs	116.421µs	117.281µs	117.476µs	118.980µs	2.91%	-0.468	-0.012	1.13%	0.092µs	1	200
credit_card/is_card_number/ 3782-8224-6310-005	throughput	8404802.330op/s	8664062.053op/s ± 98278.412op/s	8649795.806op/s ± 66334.279op/s	8726519.700op/s	8821113.363op/s	8925734.573op/s	8966507.004op/s	3.66%	0.528	0.068	1.13%	6949.333op/s	1	200
credit_card/is_card_number/ 378282246310005	execution_time	104.479µs	107.225µs ± 1.357µs	107.177µs ± 0.937µs	108.113µs	109.517µs	110.258µs	110.365µs	2.97%	0.147	-0.557	1.26%	0.096µs	1	200
credit_card/is_card_number/ 378282246310005	throughput	9060860.337op/s	9327688.817op/s ± 117847.134op/s	9330334.375op/s ± 81418.314op/s	9413327.187op/s	9521538.230op/s	9558492.687op/s	9571316.186op/s	2.58%	-0.093	-0.576	1.26%	8333.051op/s	1	200
credit_card/is_card_number/37828224631	execution_time	2.415µs	2.417µs ± 0.002µs	2.416µs ± 0.001µs	2.417µs	2.418µs	2.424µs	2.433µs	0.69%	6.251	55.907	0.07%	0.000µs	1	200
credit_card/is_card_number/37828224631	throughput	410996637.553op/s	413799955.140op/s ± 275791.244op/s	413825511.409op/s ± 120622.888op/s	413954724.815op/s	414016382.078op/s	414040319.921op/s	414044501.531op/s	0.05%	-6.214	55.371	0.07%	19501.386op/s	1	200
credit_card/is_card_number/378282246310005	execution_time	100.775µs	105.851µs ± 1.603µs	106.205µs ± 0.917µs	107.054µs	107.720µs	108.045µs	108.239µs	1.92%	-0.968	0.336	1.51%	0.113µs	1	200
credit_card/is_card_number/378282246310005	throughput	9238786.253op/s	9449451.459op/s ± 145298.242op/s	9415782.927op/s ± 80616.298op/s	9522983.721op/s	9772232.715op/s	9832194.366op/s	9923079.422op/s	5.39%	1.033	0.494	1.53%	10274.137op/s	1	200
credit_card/is_card_number/37828224631000521389798	execution_time	104.670µs	106.570µs ± 0.382µs	106.600µs ± 0.217µs	106.819µs	107.080µs	107.281µs	107.464µs	0.81%	-1.013	2.764	0.36%	0.027µs	1	200
credit_card/is_card_number/37828224631000521389798	throughput	9305475.906op/s	9383617.797op/s ± 33766.564op/s	9380848.997op/s ± 19116.604op/s	9398502.203op/s	9448621.235op/s	9470090.588op/s	9553800.909op/s	1.84%	1.054	2.936	0.36%	2387.657op/s	1	200
credit_card/is_card_number/x371413321323331	execution_time	21.801µs	22.429µs ± 0.365µs	22.390µs ± 0.268µs	22.660µs	23.108µs	23.256µs	23.429µs	4.64%	0.424	-0.510	1.62%	0.026µs	1	200
credit_card/is_card_number/x371413321323331	throughput	42681386.657op/s	44596571.254op/s ± 721208.985op/s	44663634.261op/s ± 537975.472op/s	45201589.953op/s	45678497.770op/s	45816047.583op/s	45868722.254op/s	2.70%	-0.361	-0.587	1.61%	50997.176op/s	1	200
credit_card/is_card_number_no_luhn/	execution_time	2.415µs	2.416µs ± 0.001µs	2.416µs ± 0.001µs	2.417µs	2.418µs	2.419µs	2.420µs	0.14%	0.995	0.679	0.04%	0.000µs	1	200
credit_card/is_card_number_no_luhn/	throughput	413295596.520op/s	413832669.158op/s ± 154553.581op/s	413864014.542op/s ± 102240.757op/s	413959899.998op/s	414005335.377op/s	414065642.821op/s	414075858.017op/s	0.05%	-0.993	0.673	0.04%	10928.589op/s	1	200
credit_card/is_card_number_no_luhn/ 3782-8224-6310-005	execution_time	86.952µs	87.318µs ± 0.284µs	87.277µs ± 0.083µs	87.350µs	87.711µs	88.910µs	89.125µs	2.12%	3.917	19.280	0.32%	0.020µs	1	200
credit_card/is_card_number_no_luhn/ 3782-8224-6310-005	throughput	11220231.385op/s	11452538.082op/s ± 36795.634op/s	11457802.062op/s ± 10891.792op/s	11470051.696op/s	11485491.419op/s	11498619.661op/s	11500660.138op/s	0.37%	-3.860	18.825	0.32%	2601.844op/s	1	200
credit_card/is_card_number_no_luhn/ 378282246310005	execution_time	79.655µs	80.269µs ± 0.600µs	80.092µs ± 0.271µs	80.444µs	81.417µs	82.447µs	83.105µs	3.76%	2.141	5.539	0.75%	0.042µs	1	200
credit_card/is_card_number_no_luhn/ 378282246310005	throughput	12032978.447op/s	12458819.826op/s ± 91687.980op/s	12485622.805op/s ± 42273.877op/s	12522188.074op/s	12544908.389op/s	12553816.668op/s	12554209.075op/s	0.55%	-2.077	5.199	0.73%	6483.319op/s	1	200
credit_card/is_card_number_no_luhn/37828224631	execution_time	2.415µs	2.417µs ± 0.001µs	2.416µs ± 0.001µs	2.417µs	2.419µs	2.422µs	2.426µs	0.39%	2.876	11.688	0.06%	0.000µs	1	200
credit_card/is_card_number_no_luhn/37828224631	throughput	412251694.052op/s	413794652.150op/s ± 243004.992op/s	413855551.914op/s ± 106183.619op/s	413940203.944op/s	414021560.870op/s	414058519.822op/s	414104360.502op/s	0.06%	-2.867	11.613	0.06%	17183.048op/s	1	200
credit_card/is_card_number_no_luhn/378282246310005	execution_time	76.684µs	77.050µs ± 0.411µs	76.942µs ± 0.120µs	77.098µs	77.667µs	78.979µs	79.089µs	2.79%	3.435	12.516	0.53%	0.029µs	1	200
credit_card/is_card_number_no_luhn/378282246310005	throughput	12644011.645op/s	12979008.915op/s ± 68078.212op/s	12996871.003op/s ± 20324.811op/s	13013387.848op/s	13026762.704op/s	13032291.438op/s	13040507.729op/s	0.34%	-3.391	12.243	0.52%	4813.857op/s	1	200
credit_card/is_card_number_no_luhn/37828224631000521389798	execution_time	105.420µs	106.609µs ± 0.436µs	106.647µs ± 0.302µs	106.924µs	107.235µs	107.568µs	107.759µs	1.04%	-0.232	0.005	0.41%	0.031µs	1	200
credit_card/is_card_number_no_luhn/37828224631000521389798	throughput	9279969.167op/s	9380197.287op/s ± 38419.604op/s	9376760.226op/s ± 26564.169op/s	9406400.883op/s	9437873.763op/s	9482877.336op/s	9485869.889op/s	1.16%	0.256	0.023	0.41%	2716.676op/s	1	200
credit_card/is_card_number_no_luhn/x371413321323331	execution_time	21.696µs	22.592µs ± 0.430µs	22.564µs ± 0.288µs	22.869µs	23.354µs	23.584µs	23.730µs	5.17%	0.225	-0.282	1.90%	0.030µs	1	200
credit_card/is_card_number_no_luhn/x371413321323331	throughput	42140958.309op/s	44279788.663op/s ± 839324.608op/s	44319311.361op/s ± 563889.398op/s	44833197.305op/s	45712186.766op/s	45873378.895op/s	46091757.988op/s	4.00%	-0.131	-0.345	1.89%	59349.212op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
credit_card/is_card_number/	execution_time	[2.416µs; 2.417µs] or [-0.005%; +0.005%]	None	None	None
credit_card/is_card_number/	throughput	[413802825.755op/s; 413847366.758op/s] or [-0.005%; +0.005%]	None	None	None
credit_card/is_card_number/ 3782-8224-6310-005	execution_time	[115.254µs; 115.614µs] or [-0.156%; +0.156%]	None	None	None
credit_card/is_card_number/ 3782-8224-6310-005	throughput	[8650441.610op/s; 8677682.496op/s] or [-0.157%; +0.157%]	None	None	None
credit_card/is_card_number/ 378282246310005	execution_time	[107.037µs; 107.413µs] or [-0.175%; +0.175%]	None	None	None
credit_card/is_card_number/ 378282246310005	throughput	[9311356.337op/s; 9344021.296op/s] or [-0.175%; +0.175%]	None	None	None
credit_card/is_card_number/37828224631	execution_time	[2.416µs; 2.417µs] or [-0.009%; +0.009%]	None	None	None
credit_card/is_card_number/37828224631	throughput	[413761733.126op/s; 413838177.154op/s] or [-0.009%; +0.009%]	None	None	None
credit_card/is_card_number/378282246310005	execution_time	[105.629µs; 106.073µs] or [-0.210%; +0.210%]	None	None	None
credit_card/is_card_number/378282246310005	throughput	[9429314.520op/s; 9469588.398op/s] or [-0.213%; +0.213%]	None	None	None
credit_card/is_card_number/37828224631000521389798	execution_time	[106.517µs; 106.623µs] or [-0.050%; +0.050%]	None	None	None
credit_card/is_card_number/37828224631000521389798	throughput	[9378938.076op/s; 9388297.518op/s] or [-0.050%; +0.050%]	None	None	None
credit_card/is_card_number/x371413321323331	execution_time	[22.379µs; 22.480µs] or [-0.226%; +0.226%]	None	None	None
credit_card/is_card_number/x371413321323331	throughput	[44496618.625op/s; 44696523.883op/s] or [-0.224%; +0.224%]	None	None	None
credit_card/is_card_number_no_luhn/	execution_time	[2.416µs; 2.417µs] or [-0.005%; +0.005%]	None	None	None
credit_card/is_card_number_no_luhn/	throughput	[413811249.518op/s; 413854088.798op/s] or [-0.005%; +0.005%]	None	None	None
credit_card/is_card_number_no_luhn/ 3782-8224-6310-005	execution_time	[87.278µs; 87.357µs] or [-0.045%; +0.045%]	None	None	None
credit_card/is_card_number_no_luhn/ 3782-8224-6310-005	throughput	[11447438.561op/s; 11457637.603op/s] or [-0.045%; +0.045%]	None	None	None
credit_card/is_card_number_no_luhn/ 378282246310005	execution_time	[80.186µs; 80.352µs] or [-0.104%; +0.104%]	None	None	None
credit_card/is_card_number_no_luhn/ 378282246310005	throughput	[12446112.754op/s; 12471526.899op/s] or [-0.102%; +0.102%]	None	None	None
credit_card/is_card_number_no_luhn/37828224631	execution_time	[2.416µs; 2.417µs] or [-0.008%; +0.008%]	None	None	None
credit_card/is_card_number_no_luhn/37828224631	throughput	[413760973.995op/s; 413828330.305op/s] or [-0.008%; +0.008%]	None	None	None
credit_card/is_card_number_no_luhn/378282246310005	execution_time	[76.993µs; 77.107µs] or [-0.074%; +0.074%]	None	None	None
credit_card/is_card_number_no_luhn/378282246310005	throughput	[12969573.929op/s; 12988443.900op/s] or [-0.073%; +0.073%]	None	None	None
credit_card/is_card_number_no_luhn/37828224631000521389798	execution_time	[106.549µs; 106.670µs] or [-0.057%; +0.057%]	None	None	None
credit_card/is_card_number_no_luhn/37828224631000521389798	throughput	[9374872.699op/s; 9385521.875op/s] or [-0.057%; +0.057%]	None	None	None
credit_card/is_card_number_no_luhn/x371413321323331	execution_time	[22.532µs; 22.651µs] or [-0.264%; +0.264%]	None	None	None
credit_card/is_card_number_no_luhn/x371413321323331	throughput	[44163466.344op/s; 44396110.981op/s] or [-0.263%; +0.263%]	None	None	None

Group 2

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
tags/replace_trace_tags	execution_time	2.685µs	2.736µs ± 0.017µs	2.739µs ± 0.008µs	2.747µs	2.756µs	2.762µs	2.765µs	0.93%	-1.115	0.944	0.62%	0.001µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
tags/replace_trace_tags	execution_time	[2.733µs; 2.738µs] or [-0.087%; +0.087%]	None	None	None

Group 3

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
write only interface	execution_time	1.355µs	3.162µs ± 1.528µs	3.007µs ± 0.024µs	3.030µs	3.084µs	13.712µs	17.404µs	478.73%	7.941	63.568	48.21%	0.108µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
write only interface	execution_time	[2.950µs; 3.373µs] or [-6.699%; +6.699%]	None	None	None

Group 4

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
benching deserializing traces from msgpack to their internal representation	execution_time	1.134µs	1.197µs ± 0.023µs	1.203µs ± 0.013µs	1.215µs	1.218µs	1.219µs	1.220µs	1.37%	-1.318	0.985	1.89%	0.002µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
benching deserializing traces from msgpack to their internal representation	execution_time	[1.194µs; 1.200µs] or [-0.263%; +0.263%]	None	None	None

Group 5

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
normalization/normalize_name/normalize_name/Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Lo...	execution_time	275.753µs	276.316µs ± 0.177µs	276.285µs ± 0.111µs	276.420µs	276.611µs	276.760µs	276.994µs	0.26%	0.603	0.877	0.06%	0.013µs	1	200
normalization/normalize_name/normalize_name/Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Lo...	throughput	3610180.660op/s	3619046.381op/s ± 2320.558op/s	3619452.962op/s ± 1455.864op/s	3620475.989op/s	3622096.528op/s	3622904.003op/s	3626437.429op/s	0.19%	-0.598	0.871	0.06%	164.088op/s	1	200
normalization/normalize_name/normalize_name/bad-name	execution_time	28.057µs	28.117µs ± 0.038µs	28.114µs ± 0.028µs	28.139µs	28.192µs	28.228µs	28.235µs	0.43%	0.950	0.385	0.14%	0.003µs	1	200
normalization/normalize_name/normalize_name/bad-name	throughput	35417313.004op/s	35565659.788op/s ± 48621.714op/s	35569607.414op/s ± 34999.773op/s	35605250.747op/s	35622057.982op/s	35625867.987op/s	35641851.485op/s	0.20%	-0.944	0.368	0.14%	3438.074op/s	1	200
normalization/normalize_name/normalize_name/good	execution_time	16.501µs	16.546µs ± 0.038µs	16.532µs ± 0.018µs	16.563µs	16.622µs	16.691µs	16.712µs	1.09%	1.719	3.410	0.23%	0.003µs	1	200
normalization/normalize_name/normalize_name/good	throughput	59837182.014op/s	60436485.328op/s ± 139719.160op/s	60490221.995op/s ± 64670.227op/s	60539123.991op/s	60562744.402op/s	60589590.021op/s	60600893.812op/s	0.18%	-1.702	3.327	0.23%	9879.637op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
normalization/normalize_name/normalize_name/Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Lo...	execution_time	[276.291µs; 276.341µs] or [-0.009%; +0.009%]	None	None	None
normalization/normalize_name/normalize_name/Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Long-.Too-Lo...	throughput	[3618724.774op/s; 3619367.988op/s] or [-0.009%; +0.009%]	None	None	None
normalization/normalize_name/normalize_name/bad-name	execution_time	[28.112µs; 28.122µs] or [-0.019%; +0.019%]	None	None	None
normalization/normalize_name/normalize_name/bad-name	throughput	[35558921.286op/s; 35572398.290op/s] or [-0.019%; +0.019%]	None	None	None
normalization/normalize_name/normalize_name/good	execution_time	[16.541µs; 16.552µs] or [-0.032%; +0.032%]	None	None	None
normalization/normalize_name/normalize_name/good	throughput	[60417121.596op/s; 60455849.060op/s] or [-0.032%; +0.032%]	None	None	None

Group 6

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
two way interface	execution_time	17.623µs	21.389µs ± 8.256µs	17.852µs ± 0.118µs	18.021µs	36.040µs	36.837µs	89.037µs	398.74%	3.582	21.298	38.50%	0.584µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
two way interface	execution_time	[20.245µs; 22.533µs] or [-5.350%; +5.350%]	None	None	None

Group 7

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
normalization/normalize_trace/test_trace	execution_time	297.770ns	307.419ns ± 12.288ns	301.949ns ± 2.725ns	307.318ns	336.712ns	344.938ns	345.924ns	14.56%	1.860	2.239	3.99%	0.869ns	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
normalization/normalize_trace/test_trace	execution_time	[305.716ns; 309.122ns] or [-0.554%; +0.554%]	None	None	None

Group 8

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
concentrator/add_spans_to_concentrator	execution_time	8.986ms	9.024ms ± 0.016ms	9.024ms ± 0.009ms	9.033ms	9.049ms	9.065ms	9.091ms	0.74%	0.521	1.292	0.17%	0.001ms	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
concentrator/add_spans_to_concentrator	execution_time	[9.022ms; 9.026ms] or [-0.024%; +0.024%]	None	None	None

Group 9

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
redis/obfuscate_redis_string	execution_time	38.977µs	39.540µs ± 1.009µs	39.085µs ± 0.043µs	39.136µs	41.715µs	41.781µs	42.320µs	8.28%	1.709	0.957	2.55%	0.071µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
redis/obfuscate_redis_string	execution_time	[39.400µs; 39.680µs] or [-0.354%; +0.354%]	None	None	None

Group 10

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
normalization/normalize_service/normalize_service/A0000000000000000000000000000000000000000000000000...	execution_time	537.570µs	538.119µs ± 0.316µs	538.063µs ± 0.179µs	538.291µs	538.652µs	539.287µs	539.402µs	0.25%	1.074	2.231	0.06%	0.022µs	1	200
normalization/normalize_service/normalize_service/A0000000000000000000000000000000000000000000000000...	throughput	1853903.667op/s	1858325.513op/s ± 1092.111op/s	1858518.427op/s ± 616.757op/s	1859040.191op/s	1859927.900op/s	1860124.765op/s	1860221.633op/s	0.09%	-1.069	2.211	0.06%	77.224op/s	1	200
normalization/normalize_service/normalize_service/Data🐨dog🐶 繋がっ⛰てて	execution_time	466.780µs	467.294µs ± 0.235µs	467.310µs ± 0.146µs	467.439µs	467.661µs	467.849µs	468.062µs	0.16%	0.087	-0.001	0.05%	0.017µs	1	200
normalization/normalize_service/normalize_service/Data🐨dog🐶 繋がっ⛰てて	throughput	2136468.139op/s	2139982.403op/s ± 1076.974op/s	2139906.043op/s ± 667.600op/s	2140721.331op/s	2141876.960op/s	2142190.134op/s	2142337.586op/s	0.11%	-0.084	-0.004	0.05%	76.154op/s	1	200
normalization/normalize_service/normalize_service/Test Conversion 0f Weird !@#$%^&**() Characters	execution_time	184.535µs	185.075µs ± 0.234µs	185.066µs ± 0.141µs	185.205µs	185.481µs	185.659µs	186.033µs	0.52%	0.722	1.238	0.13%	0.017µs	1	200
normalization/normalize_service/normalize_service/Test Conversion 0f Weird !@#$%^&**() Characters	throughput	5375385.331op/s	5403211.351op/s ± 6838.464op/s	5403488.994op/s ± 4126.861op/s	5407801.098op/s	5413654.352op/s	5415765.137op/s	5419024.733op/s	0.29%	-0.711	1.209	0.13%	483.552op/s	1	200
normalization/normalize_service/normalize_service/[empty string]	execution_time	44.666µs	44.731µs ± 0.033µs	44.728µs ± 0.023µs	44.753µs	44.793µs	44.809µs	44.835µs	0.24%	0.374	-0.040	0.07%	0.002µs	1	200
normalization/normalize_service/normalize_service/[empty string]	throughput	22304038.357op/s	22355723.231op/s ± 16429.691op/s	22357522.583op/s ± 11402.343op/s	22366750.188op/s	22382435.768op/s	22386417.638op/s	22388635.716op/s	0.14%	-0.370	-0.045	0.07%	1161.755op/s	1	200
normalization/normalize_service/normalize_service/test_ASCII	execution_time	49.737µs	49.826µs ± 0.098µs	49.812µs ± 0.053µs	49.867µs	49.934µs	49.998µs	50.888µs	2.16%	6.427	66.122	0.20%	0.007µs	1	200
normalization/normalize_service/normalize_service/test_ASCII	throughput	19650850.093op/s	20069820.412op/s ± 39120.204op/s	20075577.549op/s ± 21559.953op/s	20095366.535op/s	20102298.023op/s	20104506.075op/s	20105737.476op/s	0.15%	-6.270	63.843	0.19%	2766.216op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
normalization/normalize_service/normalize_service/A0000000000000000000000000000000000000000000000000...	execution_time	[538.075µs; 538.163µs] or [-0.008%; +0.008%]	None	None	None
normalization/normalize_service/normalize_service/A0000000000000000000000000000000000000000000000000...	throughput	[1858174.157op/s; 1858476.869op/s] or [-0.008%; +0.008%]	None	None	None
normalization/normalize_service/normalize_service/Data🐨dog🐶 繋がっ⛰てて	execution_time	[467.261µs; 467.326µs] or [-0.007%; +0.007%]	None	None	None
normalization/normalize_service/normalize_service/Data🐨dog🐶 繋がっ⛰てて	throughput	[2139833.144op/s; 2140131.661op/s] or [-0.007%; +0.007%]	None	None	None
normalization/normalize_service/normalize_service/Test Conversion 0f Weird !@#$%^&**() Characters	execution_time	[185.043µs; 185.108µs] or [-0.018%; +0.018%]	None	None	None
normalization/normalize_service/normalize_service/Test Conversion 0f Weird !@#$%^&**() Characters	throughput	[5402263.606op/s; 5404159.096op/s] or [-0.018%; +0.018%]	None	None	None
normalization/normalize_service/normalize_service/[empty string]	execution_time	[44.727µs; 44.736µs] or [-0.010%; +0.010%]	None	None	None
normalization/normalize_service/normalize_service/[empty string]	throughput	[22353446.234op/s; 22358000.228op/s] or [-0.010%; +0.010%]	None	None	None
normalization/normalize_service/normalize_service/test_ASCII	execution_time	[49.813µs; 49.840µs] or [-0.027%; +0.027%]	None	None	None
normalization/normalize_service/normalize_service/test_ASCII	throughput	[20064398.728op/s; 20075242.096op/s] or [-0.027%; +0.027%]	None	None	None

Group 11

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
sql/obfuscate_sql_string	execution_time	72.101µs	72.223µs ± 0.143µs	72.202µs ± 0.028µs	72.231µs	72.314µs	72.781µs	73.868µs	2.31%	8.334	87.120	0.20%	0.010µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
sql/obfuscate_sql_string	execution_time	[72.203µs; 72.243µs] or [-0.028%; +0.028%]	None	None	None

Group 12

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	3475380	1726819201	vianney/data-pipeline/APMSP-1013-stats-can-be-computed-from-the-spans-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
benching string interning on wordpress profile	execution_time	143.893µs	144.690µs ± 0.415µs	144.585µs ± 0.167µs	144.804µs	145.471µs	145.974µs	147.932µs	2.31%	3.068	18.268	0.29%	0.029µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
benching string interning on wordpress profile	execution_time	[144.633µs; 144.748µs] or [-0.040%; +0.040%]	None	None	None

Baseline

Omitted due to size.

[bantonsson]

You need to rebase on main if you want the benchmarks numbers to make sense.

And I see your PR is into your own branch, so I'll keep quiet...

[ajgajg1134]

Overall this looks good to me just a few small comments!

Is there anyway to run this with a real test application / real traces+stats and make sure they show up in the datadog UI? The unit tests look good but it's always nice to have a smoke test or equivalent

[ekump]

non-blocking nit: I prefer putting the ticket ID right after the TODO.