datadog-agent
datadog-agent copied to clipboard
DataDog
[ASCII-2415] Add merged CPU profiles for each agent process and use PGO
What does this PR do?
Same as https://github.com/DataDog/datadog-agent/pull/30313 but using merged profiles from prod.
Motivation
Describe how to test/QA your changes
Possible Drawbacks / Trade-offs
Additional Notes
[Fast Unit Tests Report]
On pipeline 47259010 (CI Visibility). The following jobs did not run any unit tests:
Jobs:
- tests_deb-arm64-py3
- tests_deb-x64-py3
- tests_flavor_dogstatsd_deb-x64
- tests_flavor_heroku_deb-x64
- tests_flavor_iot_deb-x64
- tests_rpm-arm64-py3
- tests_rpm-x64-py3
- tests_windows-x64
If you modified Go files and expected unit tests to run in these jobs, please double check the job logs. If you think tests should have been executed reach out to #agent-devx-help
![agent-platform-auto-pr[bot] avatar](https://avatars.githubusercontent.com/u/365230?v=4 "Published by a pub.dev verified publisher"){kind=small}
Regression Detector
Regression Detector Results
Run ID: fa54db5e-6e9a-4f8b-9708-1b456de444f2 Metrics dashboard Target profiles
Baseline: b9db97adc910e802e8cc6704d768652c4f80bc06 Comparison: aae1dbfab6ba25d3ecabb6a2f0cc83673cb9ec53
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
Significant changes in experiment optimization goals
Confidence level: 90.00% Effect size tolerance: |Δ mean %| ≥ 5.00%
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ❌ | tcp_syslog_to_blackhole | ingress throughput | -8.90 | [-8.95, -8.84] | 1 | Logs |
Fine details of change detection per experiment
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | file_tree | memory utilization | +2.56 | [+2.44, +2.68] | 1 | Logs |
| ➖ | otel_to_otel_logs | ingress throughput | +0.05 | [-0.78, +0.88] | 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 | [-0.00, +0.00] | 1 | Logs |
| ➖ | pycheck_lots_of_tags | % cpu utilization | -1.03 | [-3.55, +1.49] | 1 | Logs |
| ➖ | idle | memory utilization | -1.06 | [-1.12, -1.00] | 1 | Logs |
| ➖ | basic_py_check | % cpu utilization | -1.73 | [-4.35, +0.89] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_cpu | % cpu utilization | -4.31 | [-5.05, -3.57] | 1 | Logs |
| ❌ | tcp_syslog_to_blackhole | ingress throughput | -8.90 | [-8.95, -8.84] | 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".
Regression Detector Results
Run ID: f9ba7d3a-26ae-469b-845e-effef8ec6509 Metrics dashboard Target profiles
Baseline: 7.58.0 Comparison: 7-58-1-beta-pgo-prod-profiles-merged-py3
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
Significant changes in experiment optimization goals
Confidence level: 90.00% Effect size tolerance: |Δ mean %| ≥ 5.00%
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ❌ | tcp_syslog_to_blackhole | ingress throughput | -9.08 | [-9.10, -9.06] | 1 | Logs |
Fine details of change detection per experiment
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | idle_all_features | memory utilization | +0.60 | [+0.56, +0.64] | 1 | Logs bounds checks dashboard |
| ➖ | quality_gate_idle_all_features | memory utilization | +0.45 | [+0.41, +0.49] | 1 | Logs bounds checks dashboard |
| ➖ | idle | memory utilization | +0.22 | [+0.20, +0.25] | 1 | Logs bounds checks dashboard |
| ➖ | basic_py_check | % cpu utilization | +0.13 | [-1.06, +1.33] | 1 | Logs |
| ➖ | file_to_blackhole_1000ms_latency | egress throughput | +0.09 | [-0.13, +0.30] | 1 | Logs |
| ➖ | file_to_blackhole_0ms_latency | egress throughput | +0.02 | [-0.13, +0.17] | 1 | Logs |
| ➖ | file_to_blackhole_500ms_latency | egress throughput | +0.02 | [-0.09, +0.13] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api | ingress throughput | +0.00 | [-0.04, +0.05] | 1 | Logs |
| ➖ | tcp_dd_logs_filter_exclude | ingress throughput | +0.00 | [-0.00, +0.00] | 1 | Logs |
| ➖ | quality_gate_idle | memory utilization | -0.01 | [-0.04, +0.01] | 1 | Logs bounds checks dashboard |
| ➖ | file_to_blackhole_300ms_latency | egress throughput | -0.04 | [-0.13, +0.04] | 1 | Logs |
| ➖ | file_to_blackhole_100ms_latency | egress throughput | -0.11 | [-0.21, -0.00] | 1 | Logs |
| ➖ | otel_to_otel_logs | ingress throughput | -0.63 | [-0.99, -0.27] | 1 | Logs |
| ➖ | file_tree | memory utilization | -0.64 | [-0.69, -0.59] | 1 | Logs |
| ➖ | pycheck_lots_of_tags | % cpu utilization | -1.39 | [-2.48, -0.30] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_cpu | % cpu utilization | -4.06 | [-4.39, -3.74] | 1 | Logs |
| ❌ | tcp_syslog_to_blackhole | ingress throughput | -9.08 | [-9.10, -9.06] | 1 | Logs |
Bounds Checks
| perf | experiment | bounds_check_name | replicates_passed |
|---|---|---|---|
| ❌ | idle | memory_usage | 20/50 |
| ❌ | quality_gate_idle | memory_usage | 27/50 |
| ✅ | file_to_blackhole_0ms_latency | memory_usage | 50/50 |
| ✅ | file_to_blackhole_1000ms_latency | memory_usage | 50/50 |
| ✅ | file_to_blackhole_100ms_latency | memory_usage | 50/50 |
| ✅ | file_to_blackhole_300ms_latency | memory_usage | 50/50 |
| ✅ | file_to_blackhole_500ms_latency | memory_usage | 50/50 |
| ✅ | idle_all_features | memory_usage | 50/50 |
| ✅ | quality_gate_idle_all_features | memory_usage | 50/50 |
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".