datadog-agent
datadog-agent copied to clipboard
DataDog
workload policy from multiple activity dumps
What does this PR do?
Motivation
Additional Notes
Possible Drawbacks / Trade-offs
Describe how to test/QA your changes
Regression Detector
Regression Detector Results
Run ID: f89b0169-ef36-4d9e-b2c4-c14c5e4237bd Metrics dashboard Target profiles
Baseline: 06338e9bfc7594ed45344e69ff29a01945bacded Comparison: a963b2c3f93e8ab473c7fc91ad0f450f9f994f77
Performance changes are noted in the perf column of each table:
- ✅ = significantly better comparison variant performance
- ❌ = significantly worse comparison variant performance
- ➖ = no significant change in performance
No significant changes in experiment optimization goals
Confidence level: 90.00% Effect size tolerance: |Δ mean %| ≥ 5.00%
There were no significant changes in experiment optimization goals at this confidence level and effect size tolerance.
Fine details of change detection per experiment
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | pycheck_lots_of_tags | % cpu utilization | +1.39 | [-1.15, +3.93] | 1 | Logs |
| ➖ | otel_to_otel_logs | ingress throughput | +1.17 | [+0.36, +1.98] | 1 | Logs |
| ➖ | tcp_syslog_to_blackhole | ingress throughput | +0.38 | [+0.33, +0.44] | 1 | Logs |
| ➖ | idle | memory utilization | +0.27 | [+0.22, +0.32] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_cpu | % cpu utilization | +0.11 | [-0.64, +0.86] | 1 | Logs |
| ➖ | tcp_dd_logs_filter_exclude | ingress throughput | +0.00 | [-0.01, +0.01] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api | ingress throughput | -0.00 | [-0.09, +0.08] | 1 | Logs |
| ➖ | basic_py_check | % cpu utilization | -0.12 | [-2.87, +2.63] | 1 | Logs |
| ➖ | file_tree | memory utilization | -0.91 | [-1.02, -0.80] | 1 | Logs |
Bounds Checks
| perf | experiment | bounds_check_name | replicates_passed |
|---|---|---|---|
| ✅ | idle | memory_usage | 10/10 |
Explanation
A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".
For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:
-
Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.
-
Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.
-
Its configuration does not mark it "erratic".
![pr-commenter[bot] avatar](https://avatars.githubusercontent.com/u/365230?v=4 "Published by a pub.dev verified publisher"){kind=small}
Test changes on VM
Use this command from test-infra-definitions to manually test this PR changes on a VM:
inv create-vm --pipeline-id=44896611 --os-family=ubuntu
Note: This applies to commit a963b2c3
:warning::rotating_light: Warning, this pull request increases the binary size of serverless extension by 332704 bytes. Each MB of binary size increase means about 10ms of additional cold start time, so this pull request would increase cold start time by 3ms.
Debug info
If you have questions, we are happy to help, come visit us in the #serverless slack channel and provide a link to this comment.
We suggest you consider adding the !serverless build tag to remove any new dependencies not needed in the serverless extension.
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
:warning::rotating_light: Warning, this pull request increases the binary size of serverless extension by 332704 bytes. Each MB of binary size increase means about 10ms of additional cold start time, so this pull request would increase cold start time by 3ms.
Debug info
If you have questions, we are happy to help, come visit us in the #serverless slack channel and provide a link to this comment.
We suggest you consider adding the !serverless build tag to remove any new dependencies not needed in the serverless extension.
Serverless Benchmark Results
BenchmarkStartEndInvocation comparison between ea7ff2e8d9578d95525d192859074185ac94932e and fb5c79106fb6310346af0dc7ccff8f27c537014c.
tl;dr
Use these benchmarks as an insight tool during development.
-
Skim down the
vs basecolumn in each chart. If there is a~, then there was no statistically significant change to the benchmark. Otherwise, ensure the estimated percent change is either negative or very small. -
The last row of each chart is the
geomean. Ensure this percentage is either negative or very small.
What is this benchmarking?
The BenchmarkStartEndInvocation compares the amount of time it takes to call the start-invocation and end-invocation endpoints. For universal instrumentation languages (Dotnet, Golang, Java, Ruby), this represents the majority of the duration overhead added by our tracing layer.
The benchmark is run using a large variety of lambda request payloads. In the charts below, there is one row for each event payload type.
How do I interpret these charts?
The charts below comes from benchstat. They represent the statistical change in duration (sec/op), memory overhead (B/op), and allocations (allocs/op).
The benchstat docs explain how to interpret these charts.
Before the comparison table, we see common file-level configuration. If there are benchmarks with different configuration (for example, from different packages), benchstat will print separate tables for each configuration.
The table then compares the two input files for each benchmark. It shows the median and 95% confidence interval summaries for each benchmark before and after the change, and an A/B comparison under "vs base". ... The p-value measures how likely it is that any differences were due to random chance (i.e., noise). The "~" means benchstat did not detect a statistically significant difference between the two inputs. ...
Note that "statistically significant" is not the same as "large": with enough low-noise data, even very small changes can be distinguished from noise and considered statistically significant. It is, of course, generally easier to distinguish large changes from noise.
Finally, the last row of the table shows the geometric mean of each column, giving an overall picture of how the benchmarks changed. Proportional changes in the geomean reflect proportional changes in the benchmarks. For example, given n benchmarks, if sec/op for one of them increases by a factor of 2, then the sec/op geomean will increase by a factor of ⁿ√2.
I need more help
First off, do not worry if the benchmarks are failing. They are not tests. The intention is for them to be a tool for you to use during development.
If you would like a hand interpreting the results come chat with us in #serverless-agent in the internal DataDog slack or in #serverless in the public DataDog slack. We're happy to help!
Benchmark stats
goos: linux
goarch: amd64
pkg: github.com/DataDog/datadog-agent/pkg/serverless/daemon
cpu: AMD EPYC 7763 64-Core Processor
│ baseline/benchmark.log │ current/benchmark.log │
│ sec/op │ sec/op vs base │
api-gateway-appsec.json 92.31µ ± 6% 87.22µ ± 6% -5.51% (p=0.035 n=10)
api-gateway-kong-appsec.json 69.62µ ± 2% 68.50µ ± 2% ~ (p=0.190 n=10)
api-gateway-kong.json 67.92µ ± 1% 66.41µ ± 1% -2.24% (p=0.002 n=10)
api-gateway-non-proxy-async.json 108.7µ ± 2% 105.9µ ± 1% -2.53% (p=0.001 n=10)
api-gateway-non-proxy.json 109.4µ ± 2% 106.8µ ± 2% -2.36% (p=0.000 n=10)
api-gateway-websocket-connect.json 73.42µ ± 1% 70.95µ ± 1% -3.36% (p=0.000 n=10)
api-gateway-websocket-default.json 66.24µ ± 1% 63.89µ ± 1% -3.55% (p=0.000 n=10)
api-gateway-websocket-disconnect.json 66.27µ ± 1% 64.02µ ± 1% -3.40% (p=0.000 n=10)
api-gateway.json 121.1µ ± 2% 116.3µ ± 1% -3.97% (p=0.001 n=10)
application-load-balancer.json 67.44µ ± 1% 65.04µ ± 1% -3.56% (p=0.000 n=10)
cloudfront.json 50.34µ ± 1% 48.40µ ± 2% -3.85% (p=0.000 n=10)
cloudwatch-events.json 40.46µ ± 1% 39.77µ ± 1% -1.70% (p=0.007 n=10)
cloudwatch-logs.json 67.87µ ± 2% 66.59µ ± 2% -1.89% (p=0.035 n=10)
custom.json 32.87µ ± 2% 32.61µ ± 2% ~ (p=0.315 n=10)
dynamodb.json 98.25µ ± 2% 95.56µ ± 1% -2.74% (p=0.000 n=10)
empty.json 31.11µ ± 2% 31.30µ ± 1% ~ (p=0.225 n=10)
eventbridge-custom.json 44.41µ ± 2% 43.78µ ± 1% ~ (p=0.105 n=10)
http-api.json 76.33µ ± 1% 74.61µ ± 1% -2.26% (p=0.000 n=10)
kinesis-batch.json 74.35µ ± 2% 72.59µ ± 2% -2.37% (p=0.002 n=10)
kinesis.json 56.50µ ± 3% 55.87µ ± 2% ~ (p=0.353 n=10)
s3.json 62.43µ ± 2% 61.69µ ± 1% -1.19% (p=0.029 n=10)
sns-batch.json 94.38µ ± 1% 92.39µ ± 1% -2.11% (p=0.002 n=10)
sns.json 66.92µ ± 1% 66.82µ ± 1% ~ (p=0.912 n=10)
snssqs.json 115.8µ ± 1% 112.1µ ± 1% -3.17% (p=0.000 n=10)
snssqs_no_dd_context.json 102.8µ ± 2% 100.9µ ± 2% ~ (p=0.063 n=10)
sqs-aws-header.json 58.18µ ± 2% 56.78µ ± 2% -2.41% (p=0.000 n=10)
sqs-batch.json 97.85µ ± 2% 96.52µ ± 1% -1.35% (p=0.011 n=10)
sqs.json 72.35µ ± 2% 70.50µ ± 2% -2.56% (p=0.011 n=10)
sqs_no_dd_context.json 64.52µ ± 1% 62.89µ ± 1% -2.52% (p=0.001 n=10)
stepfunction.json 47.57µ ± 1%
geomean 70.11µ 67.66µ -2.32%
│ baseline/benchmark.log │ current/benchmark.log │
│ B/op │ B/op vs base │
api-gateway-appsec.json 37.32Ki ± 0% 37.27Ki ± 0% -0.13% (p=0.000 n=10)
api-gateway-kong-appsec.json 26.92Ki ± 0% 26.93Ki ± 0% +0.05% (p=0.022 n=10)
api-gateway-kong.json 24.42Ki ± 0% 24.43Ki ± 0% +0.05% (p=0.012 n=10)
api-gateway-non-proxy-async.json 48.10Ki ± 0% 48.08Ki ± 0% ~ (p=0.075 n=10)
api-gateway-non-proxy.json 47.32Ki ± 0% 47.30Ki ± 0% -0.06% (p=0.003 n=10)
api-gateway-websocket-connect.json 25.50Ki ± 0% 25.51Ki ± 0% ~ (p=0.183 n=10)
api-gateway-websocket-default.json 21.41Ki ± 0% 21.41Ki ± 0% ~ (p=0.322 n=10)
api-gateway-websocket-disconnect.json 21.19Ki ± 0% 21.20Ki ± 0% ~ (p=0.516 n=10)
api-gateway.json 49.58Ki ± 0% 49.60Ki ± 0% +0.05% (p=0.006 n=10)
application-load-balancer.json 23.29Ki ± 0% 22.38Ki ± 0% -3.89% (p=0.000 n=10)
cloudfront.json 17.67Ki ± 0% 17.67Ki ± 0% ~ (p=0.868 n=10)
cloudwatch-events.json 11.73Ki ± 0% 11.72Ki ± 0% -0.07% (p=0.041 n=10)
cloudwatch-logs.json 53.37Ki ± 0% 53.40Ki ± 0% +0.05% (p=0.000 n=10)
custom.json 9.758Ki ± 0% 9.758Ki ± 0% ~ (p=0.956 n=10)
dynamodb.json 40.82Ki ± 0% 40.79Ki ± 0% -0.06% (p=0.043 n=10)
empty.json 9.318Ki ± 0% 9.328Ki ± 0% ~ (p=0.218 n=10)
eventbridge-custom.json 13.47Ki ± 0% 13.45Ki ± 0% ~ (p=0.171 n=10)
http-api.json 23.81Ki ± 0% 23.78Ki ± 0% -0.14% (p=0.011 n=10)
kinesis-batch.json 27.07Ki ± 0% 27.04Ki ± 0% ~ (p=0.184 n=10)
kinesis.json 17.84Ki ± 0% 17.85Ki ± 0% ~ (p=0.754 n=10)
s3.json 20.38Ki ± 0% 20.38Ki ± 0% ~ (p=0.796 n=10)
sns-batch.json 38.72Ki ± 0% 38.74Ki ± 0% ~ (p=0.101 n=10)
sns.json 24.02Ki ± 0% 24.08Ki ± 0% +0.27% (p=0.001 n=10)
snssqs.json 50.81Ki ± 0% 50.62Ki ± 0% -0.38% (p=0.000 n=10)
snssqs_no_dd_context.json 44.90Ki ± 0% 44.87Ki ± 0% -0.05% (p=0.017 n=10)
sqs-aws-header.json 18.93Ki ± 1% 18.88Ki ± 0% ~ (p=0.190 n=10)
sqs-batch.json 41.69Ki ± 0% 41.72Ki ± 0% ~ (p=0.424 n=10)
sqs.json 25.63Ki ± 1% 25.71Ki ± 0% +0.32% (p=0.043 n=10)
sqs_no_dd_context.json 20.74Ki ± 1% 20.71Ki ± 0% ~ (p=1.000 n=10)
stepfunction.json 14.18Ki ± 1%
geomean 25.80Ki 25.25Ki -0.15%
│ baseline/benchmark.log │ current/benchmark.log │
│ allocs/op │ allocs/op vs base │
api-gateway-appsec.json 629.0 ± 0% 629.5 ± 0% ~ (p=1.000 n=10)
api-gateway-kong-appsec.json 488.0 ± 0% 488.0 ± 0% ~ (p=1.000 n=10) ¹
api-gateway-kong.json 466.0 ± 0% 466.0 ± 0% ~ (p=1.000 n=10) ¹
api-gateway-non-proxy-async.json 726.0 ± 0% 726.0 ± 0% ~ (p=1.000 n=10)
api-gateway-non-proxy.json 716.0 ± 0% 716.0 ± 0% ~ (p=1.000 n=10)
api-gateway-websocket-connect.json 453.0 ± 0% 453.0 ± 0% ~ (p=1.000 n=10)
api-gateway-websocket-default.json 379.0 ± 0% 379.0 ± 0% ~ (p=1.000 n=10)
api-gateway-websocket-disconnect.json 370.0 ± 0% 370.0 ± 0% ~ (p=1.000 n=10) ¹
api-gateway.json 791.0 ± 0% 791.0 ± 0% ~ (p=1.000 n=10)
application-load-balancer.json 353.0 ± 0% 352.0 ± 0% -0.28% (p=0.000 n=10)
cloudfront.json 284.0 ± 0% 284.0 ± 0% ~ (p=1.000 n=10) ¹
cloudwatch-events.json 220.0 ± 0% 220.5 ± 0% ~ (p=0.650 n=10)
cloudwatch-logs.json 216.0 ± 0% 216.0 ± 0% ~ (p=0.628 n=10)
custom.json 169.0 ± 1% 169.0 ± 1% ~ (p=1.000 n=10)
dynamodb.json 589.0 ± 0% 589.0 ± 0% ~ (p=1.000 n=10)
empty.json 160.0 ± 0% 160.0 ± 0% ~ (p=1.000 n=10)
eventbridge-custom.json 254.0 ± 0% 254.0 ± 0% ~ (p=0.474 n=10)
http-api.json 433.0 ± 0% 433.0 ± 0% ~ (p=0.675 n=10)
kinesis-batch.json 391.0 ± 0% 391.0 ± 0% ~ (p=0.861 n=10)
kinesis.json 285.0 ± 0% 286.0 ± 0% ~ (p=0.156 n=10)
s3.json 358.0 ± 0% 358.0 ± 0% ~ (p=0.854 n=10)
sns-batch.json 455.5 ± 0% 455.0 ± 0% ~ (p=0.999 n=10)
sns.json 324.0 ± 0% 324.0 ± 0% ~ (p=0.303 n=10)
snssqs.json 450.0 ± 0% 438.5 ± 0% -2.56% (p=0.000 n=10)
snssqs_no_dd_context.json 400.0 ± 0% 400.0 ± 0% ~ (p=1.000 n=10)
sqs-aws-header.json 275.5 ± 1% 274.0 ± 0% ~ (p=0.078 n=10)
sqs-batch.json 504.0 ± 0% 504.0 ± 0% ~ (p=0.827 n=10)
sqs.json 352.0 ± 1% 353.0 ± 1% ~ (p=0.261 n=10)
sqs_no_dd_context.json 325.0 ± 1% 325.0 ± 0% ~ (p=0.495 n=10)
stepfunction.json 236.0 ± 1%
geomean 377.2 371.0 -0.09%
¹ all samples are equal