feat(autoscaling): CPURequestsRemoveLimitsMemoryRequestsAndLimits + cluster burstable default

[clamoriniere]

Summary

1. CPURequestsRemoveLimitsMemoryRequestsAndLimits controlled value

Implements the new CPURequestsRemoveLimitsMemoryRequestsAndLimits container controlledValues enum introduced in the datadog-operator (c59fc90).

When a container constraint sets this value, the autoscaler applies different strategies per resource:

• CPU: only requests are controlled and any existing CPU limit is removed from the live pod, allowing the container to burst freely and avoid CPU throttling
• Memory: both requests and limits are controlled (standard RequestsAndLimits semantics)

Changes:

• controller_vertical_helpers.go: strip CPU limit from the recommendation in applyVerticalConstraints when CPURequestsRemoveLimitsMemoryRequestsAndLimits is set
• pod_patcher.go: add getContainerControlledValues helper; pass controlledValues down to patchContainerResources which actively deletes any pre-existing CPU limit from the live pod

2. Cluster-level burstable default via PodAutoscalerInternalBuilder

Introduces autoscaling.workload.options.burstable (default: true) as the lowest-priority fallback in the IsBurstable() priority chain:

spec.options.burstable  >  preview annotation  >  cluster config default

The config value is read once at startup in provider.go and injected into a *PodAutoscalerInternalBuilder, which is threaded through to all three PodAutoscalerInternal construction paths (NewFromKubernetes, NewFromSettings, NewFromProfile), replacing the former standalone constructor functions. This avoids per-reconcile config lookups and ensures a single shared builder instance across the controller, config retriever, and autoscaler syncer.

Changes:

• model/pod_autoscaler.go: add clusterBurstableDefault field; introduce PodAutoscalerInternalBuilder with NewFromKubernetes, NewFromSettings, NewFromProfile methods
• config/setup/common_settings.go: register autoscaling.workload.options.burstable with default true
• provider/provider.go: create builder once from config, pass to all construction sites
• controller.go, config_retriever.go, config_retriever_settings.go, profile/autoscaler_syncer.go: accept and store *PodAutoscalerInternalBuilder

3. Dependency bump

• go.mod: bump datadog-operator/api to v0.0.0-20260503193602-adf766128732

Test plan

• TestApplyVerticalConstraints_CPURequestsRemoveLimits — CPU limit stripped from recommendation, memory limit preserved
• TestPatchContainerResources — CPU limit removed from pod, idempotent when already absent
• TestPatchPod — end-to-end CPU limit removal on a live pod container
• TestIsBurstable — priority chain: spec > annotation > cluster default
• TestNewPodAutoscalerFromProfile / TestUpdateFromProfile — builder wiring and annotation toggling
• Full package test suite passes: ./pkg/clusteragent/autoscaling/workload/...
• Linter clean

🤖 PR description and code assisted by Claude:claude-sonnet-4-6

[dd-octo-sts]

Files inventory check summary

File checks results against ancestor 37ca696e:

Results for datadog-agent_7.80.0~devel.git.429.bbaa1d6.pipeline.111425872-1_amd64.deb:

No change detected

[cit-pr-commenter-54b7da]

Regression Detector

Regression Detector Results

Metrics dashboard
Target profiles
Run ID: 82b22a2d-090e-4c1e-a2e3-2b65fafcf65e

Baseline: 37ca696
Comparison: bbaa1d6
Diff

Optimization Goals: ✅ No significant changes detected

Experiments ignored for regressions

Regressions in experiments with settings containing erratic: true are ignored.

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	docker_containers_cpu	% cpu utilization	+2.23	[-0.71, +5.17]	1	Logs

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	docker_containers_cpu	% cpu utilization	+2.23	[-0.71, +5.17]	1	Logs
➖	docker_containers_memory	memory utilization	+0.42	[+0.32, +0.52]	1	Logs
➖	ddot_metrics_sum_cumulativetodelta_exporter	memory utilization	+0.26	[+0.02, +0.50]	1	Logs
➖	quality_gate_logs	% cpu utilization	+0.17	[-0.80, +1.14]	1	Logs bounds checks dashboard
➖	ddot_metrics	memory utilization	+0.07	[-0.12, +0.26]	1	Logs
➖	quality_gate_metrics_logs	memory utilization	+0.07	[-0.19, +0.32]	1	Logs bounds checks dashboard
➖	file_to_blackhole_0ms_latency	egress throughput	+0.02	[-0.50, +0.55]	1	Logs
➖	file_to_blackhole_1000ms_latency	egress throughput	+0.02	[-0.42, +0.46]	1	Logs
➖	file_to_blackhole_500ms_latency	egress throughput	+0.00	[-0.41, +0.42]	1	Logs
➖	ddot_metrics_sum_delta	memory utilization	+0.00	[-0.20, +0.20]	1	Logs
➖	uds_dogstatsd_to_api	ingress throughput	-0.00	[-0.20, +0.20]	1	Logs
➖	quality_gate_idle	memory utilization	-0.00	[-0.05, +0.05]	1	Logs bounds checks dashboard
➖	tcp_dd_logs_filter_exclude	ingress throughput	-0.00	[-0.11, +0.11]	1	Logs
➖	file_to_blackhole_100ms_latency	egress throughput	-0.01	[-0.13, +0.12]	1	Logs
➖	otlp_ingest_metrics	memory utilization	-0.02	[-0.18, +0.14]	1	Logs
➖	uds_dogstatsd_to_api_v3	ingress throughput	-0.02	[-0.22, +0.18]	1	Logs
➖	uds_dogstatsd_20mb_12k_contexts_20_senders	memory utilization	-0.15	[-0.20, -0.10]	1	Logs
➖	otlp_ingest_logs	memory utilization	-0.18	[-0.27, -0.08]	1	Logs
➖	ddot_metrics_sum_cumulative	memory utilization	-0.20	[-0.36, -0.05]	1	Logs
➖	file_tree	memory utilization	-0.25	[-0.30, -0.20]	1	Logs
➖	ddot_logs	memory utilization	-0.29	[-0.35, -0.23]	1	Logs
➖	quality_gate_idle_all_features	memory utilization	-0.33	[-0.37, -0.29]	1	Logs bounds checks dashboard
➖	tcp_syslog_to_blackhole	ingress throughput	-1.94	[-2.21, -1.66]	1	Logs

Bounds Checks: ✅ Passed

perf	experiment	bounds_check_name	replicates_passed	observed_value	links
✅	docker_containers_cpu	simple_check_run	10/10	672 ≥ 26
✅	docker_containers_memory	memory_usage	10/10	245.45MiB ≤ 370MiB
✅	docker_containers_memory	simple_check_run	10/10	670 ≥ 26
✅	file_to_blackhole_0ms_latency	memory_usage	10/10	0.16GiB ≤ 1.20GiB
✅	file_to_blackhole_0ms_latency	missed_bytes	10/10	0B = 0B
✅	file_to_blackhole_1000ms_latency	memory_usage	10/10	0.21GiB ≤ 1.20GiB
✅	file_to_blackhole_1000ms_latency	missed_bytes	10/10	0B = 0B
✅	file_to_blackhole_100ms_latency	memory_usage	10/10	0.17GiB ≤ 1.20GiB
✅	file_to_blackhole_100ms_latency	missed_bytes	10/10	0B = 0B
✅	file_to_blackhole_500ms_latency	memory_usage	10/10	0.19GiB ≤ 1.20GiB
✅	file_to_blackhole_500ms_latency	missed_bytes	10/10	0B = 0B
✅	quality_gate_idle	intake_connections	10/10	3 ≤ 4	bounds checks dashboard
✅	quality_gate_idle	memory_usage	10/10	141.65MiB ≤ 147MiB	bounds checks dashboard
✅	quality_gate_idle_all_features	intake_connections	10/10	3 ≤ 4	bounds checks dashboard
✅	quality_gate_idle_all_features	memory_usage	10/10	478.36MiB ≤ 495MiB	bounds checks dashboard
✅	quality_gate_logs	intake_connections	10/10	4 ≤ 6	bounds checks dashboard
✅	quality_gate_logs	memory_usage	10/10	175.63MiB ≤ 195MiB	bounds checks dashboard
✅	quality_gate_logs	missed_bytes	10/10	0B = 0B	bounds checks dashboard
✅	quality_gate_metrics_logs	cpu_usage	10/10	345.27 ≤ 2000	bounds checks dashboard
✅	quality_gate_metrics_logs	intake_connections	10/10	4 ≤ 6	bounds checks dashboard
✅	quality_gate_metrics_logs	memory_usage	10/10	379.07MiB ≤ 430MiB	bounds checks dashboard
✅	quality_gate_metrics_logs	missed_bytes	10/10	0B = 0B	bounds checks dashboard

Explanation

Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%

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

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:

1. Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.

2. 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.

3. Its configuration does not mark it "erratic".

CI Pass/Fail Decision

✅ Passed. All Quality Gates passed.

• quality_gate_metrics_logs, bounds check cpu_usage: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check missed_bytes: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check missed_bytes: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check memory_usage: 10/10 replicas passed. Gate passed.

[dd-octo-sts]

This pull request has been automatically marked as stale because it has not had activity in the past 15 days.

It will be closed in 30 days if no further activity occurs. If this pull request is still relevant, adding a comment or pushing new commits will keep it open. Also, you can always reopen the pull request if you missed the window.

Thank you for your contributions!

[datadog-official]

🎯 Code Coverage (details)
• Patch Coverage: 63.64%
• Overall Coverage: 50.27% (-4.45%)

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: bbaa1d6 | Docs | Datadog PR Page | Give us feedback!}

[dd-octo-sts]

Static quality checks

✅ Please find below the results from static quality gates
Comparison made with ancestor 37ca696
📊 Static Quality Gates Dashboard
🔗 SQG Job

Successful checks

Info

	Quality gate	Change	Size (prev → curr → max)
✅	docker_cluster_agent_amd64	+32.58 KiB (0.02% increase)	206.579 → 206.610 → 207.600
✅	docker_dogstatsd_arm64	-63.74 KiB (0.17% reduction)	37.627 → 37.565 → 38.080

29 successful checks with minimal change (< 2 KiB)

	Quality gate	Current Size
✅	agent_deb_amd64	740.890 MiB
✅	agent_deb_amd64_fips	699.086 MiB
✅	agent_heroku_amd64	309.061 MiB
✅	agent_msi	607.441 MiB
✅	agent_rpm_amd64	740.873 MiB
✅	agent_rpm_amd64_fips	699.069 MiB
✅	agent_rpm_arm64	718.956 MiB
✅	agent_rpm_arm64_fips	680.235 MiB
✅	agent_suse_amd64	740.873 MiB
✅	agent_suse_amd64_fips	699.069 MiB
✅	agent_suse_arm64	718.956 MiB
✅	agent_suse_arm64_fips	680.235 MiB
✅	docker_agent_amd64	801.271 MiB
✅	docker_agent_arm64	804.178 MiB
✅	docker_agent_jmx_amd64	992.191 MiB
✅	docker_agent_jmx_arm64	983.877 MiB
✅	docker_cluster_agent_arm64	220.634 MiB
✅	docker_cws_instrumentation_amd64	7.142 MiB
✅	docker_cws_instrumentation_arm64	6.689 MiB
✅	docker_dogstatsd_amd64	39.366 MiB
✅	dogstatsd_deb_amd64	30.024 MiB
✅	dogstatsd_deb_arm64	28.165 MiB
✅	dogstatsd_rpm_amd64	30.024 MiB
✅	dogstatsd_suse_amd64	30.024 MiB
✅	iot_agent_deb_amd64	44.454 MiB
✅	iot_agent_deb_arm64	41.439 MiB
✅	iot_agent_deb_armhf	42.175 MiB
✅	iot_agent_rpm_amd64	44.455 MiB
✅	iot_agent_suse_amd64	44.455 MiB

On-wire sizes (compressed)

	Quality gate	Change	Size (prev → curr → max)
✅	agent_deb_amd64	neutral	175.226 MiB → 179.160
✅	agent_deb_amd64_fips	+37.89 KiB (0.02% increase)	166.984 → 167.021 → 174.440
✅	agent_heroku_amd64	+2.74 KiB (0.00% increase)	74.950 → 74.953 → 80.310
✅	agent_msi	neutral	140.547 MiB → 148.730
✅	agent_rpm_amd64	-28.41 KiB (0.02% reduction)	177.281 → 177.254 → 182.080
✅	agent_rpm_amd64_fips	+20.75 KiB (0.01% increase)	168.380 → 168.400 → 174.140
✅	agent_rpm_arm64	+36.9 KiB (0.02% increase)	159.364 → 159.400 → 163.610
✅	agent_rpm_arm64_fips	+22.8 KiB (0.01% increase)	151.701 → 151.723 → 156.850
✅	agent_suse_amd64	-28.41 KiB (0.02% reduction)	177.281 → 177.254 → 182.080
✅	agent_suse_amd64_fips	+20.75 KiB (0.01% increase)	168.380 → 168.400 → 174.140
✅	agent_suse_arm64	+36.9 KiB (0.02% increase)	159.364 → 159.400 → 163.610
✅	agent_suse_arm64_fips	+22.8 KiB (0.01% increase)	151.701 → 151.723 → 156.850
✅	docker_agent_amd64	-7.36 KiB (0.00% reduction)	267.701 → 267.694 → 272.990
✅	docker_agent_arm64	-9.95 KiB (0.00% reduction)	254.696 → 254.686 → 261.470
✅	docker_agent_jmx_amd64	+3.07 KiB (0.00% increase)	336.321 → 336.324 → 341.610
✅	docker_agent_jmx_arm64	-8.22 KiB (0.00% reduction)	319.328 → 319.320 → 326.050
✅	docker_cluster_agent_amd64	+11.69 KiB (0.02% increase)	72.406 → 72.418 → 73.460
✅	docker_cluster_agent_arm64	neutral	67.868 MiB → 68.680
✅	docker_cws_instrumentation_amd64	neutral	2.999 MiB → 3.330
✅	docker_cws_instrumentation_arm64	neutral	2.729 MiB → 3.090
✅	docker_dogstatsd_amd64	neutral	15.235 MiB → 15.870
✅	docker_dogstatsd_arm64	neutral	14.553 MiB → 14.890
✅	dogstatsd_deb_amd64	neutral	7.940 MiB → 8.830
✅	dogstatsd_deb_arm64	neutral	6.825 MiB → 7.750
✅	dogstatsd_rpm_amd64	neutral	7.951 MiB → 8.840
✅	dogstatsd_suse_amd64	neutral	7.951 MiB → 8.840
✅	iot_agent_deb_amd64	+2.51 KiB (0.02% increase)	11.697 → 11.700 → 13.210
✅	iot_agent_deb_arm64	neutral	9.997 MiB → 11.620
✅	iot_agent_deb_armhf	+3.51 KiB (0.03% increase)	10.207 → 10.210 → 11.780
✅	iot_agent_rpm_amd64	neutral	11.713 MiB → 13.230
✅	iot_agent_suse_amd64	neutral	11.713 MiB → 13.230

[s-alad]

lgtm for agent config file