apiVersion: datadoghq.com/v1alpha2
kind: DatadogPodAutoscaler
metadata:
  name: my-app                      # required: conventionally the workload name
  namespace: my-namespace           # required: must match the target workload
  annotations:                      # optional
    ad.datadoghq.com/tags: '{"team": "my-team"}'   # optional: tags on this DPA's telemetry
spec:
  owner: Local                      # optional: Local = this manifest is the source of truth (use for GitOps)
                                    # Remote = created and managed from the Datadog UI

  targetRef:                        # required: the workload being autoscaled - one DPA per workload
    apiVersion: apps/v1
    kind: Deployment
    name: my-app

  applyPolicy:                      # optional
    mode: Apply                     # Apply | Preview (Preview = compute recommendations, change nothing)

    scaleUp:                        # optional: horizontal, upward
      strategy: Max                 # Max | Min | Disabled
      stabilizationWindowSeconds: 600
      rules:
        - type: Percent             # Percent | Pods
          value: 50
          periodSeconds: 120        # 1..3600

    scaleDown:                      # optional: horizontal, downward
      strategy: Max
      stabilizationWindowSeconds: 600
      rules:
        - type: Percent
          value: 10
          periodSeconds: 1800

    update:                         # optional: vertical
      strategy: Auto                # Auto | Disabled | TriggerRollout
      # resizePendingPeriod: 600    # see Vertical rollout timing
      # rolloutFallbackDelay: 900   # see Vertical rollout timing

  constraints:                      # optional
    minReplicas: 3
    maxReplicas: 100
    containers:                     # optional: per-container vertical configuration
      - name: "*"                   # "*" matches all containers
        enabled: true
        controlledResources: [cpu, memory]
        controlledValues: RequestsAndLimits   # RequestsAndLimits | RequestsOnly
        minAllowed:
          cpu: "500m"
          memory: 1Gi
        maxAllowed:
          cpu: "4"
          memory: 8Gi

  objectives:                       # optional: configures horizontal scaling (also used by multidimensional). Exactly one entry.
    - type: ContainerResource       # PodResource | ContainerResource | CustomQuery
      containerResource:
        container: my-app
        name: cpu                   # cpu | memory
        value:
          type: Utilization         # Utilization | AbsoluteValue
          utilization: 65

  fallback:                         # optional: in-cluster horizontal fallback if recommendations go stale
    horizontal:
      enabled: true
      direction: ScaleUp            # ScaleUp | ScaleDown | All (default ScaleUp)
      triggers:
        staleRecommendationThresholdSeconds: 600   # 100..3600, default 600

  options:                          # optional
    burstable: false                # true = remove CPU limits, keep CPU request recommendations
    outOfMemory:
      bumpUpRatio: "1.2"            # +20% memory limit after an OOMKill (default)

  targetRef:
    apiVersion: argoproj.io/v1alpha1
    kind: Rollout
    name: my-app

apiVersion: datadoghq.com/v1alpha2
kind: DatadogPodAutoscaler
metadata:
  name: my-app
  namespace: my-namespace
spec:
  owner: Local
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: my-app
  applyPolicy:
    mode: Apply
    update:
      strategy: Auto              # required - without it, nothing vertical is applied
  constraints:
    minReplicas: 3
    maxReplicas: 60
    containers:
      - name: "*"
        controlledResources:
          - cpu                   # opts CPU into vertical rightsizing
          - memory
        controlledValues: RequestsAndLimits
  objectives:
    - type: ContainerResource
      containerResource:
        container: my-app
        name: cpu
        value:
          type: Utilization
          utilization: 65

apiVersion: datadoghq.com/v1alpha2
kind: DatadogPodAutoscaler
metadata:
  name: my-java-app
  namespace: my-namespace
spec:
  owner: Local
  targetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: my-java-app
  applyPolicy:
    mode: Apply
    update:
      strategy: Auto
  options:
    burstable: true

spec:
  options:
    outOfMemory:
      bumpUpRatio: "1.5"      # 1.2 = +20% (default), 1.5 = +50%

spec:
  constraints:
    containers:
      - name: my-app
        controlledResources: [cpu, memory]
        controlledValues: RequestsOnly     # limits are not right-sized

spec:
  constraints:
    minReplicas: 2
    maxReplicas: 100
    containers:
      - name: api
        enabled: true
        minAllowed:
          cpu: "1"
          memory: 1Gi
        maxAllowed:
          cpu: "4"
          memory: 5Gi
      - name: worker
        enabled: true          # no bounds - recommendations are unconstrained

spec:
  constraints:
    containers:
      - name: my-app
        enabled: true
      - name: istio-proxy
        enabled: false          # resources for this container are never modified

      - name: istio-proxy
        controlledResources: []   # empty list is equivalent to enabled: false

spec:
  constraints:
    containers:
      - name: "*"
        enabled: true
        controlledResources: [cpu, memory]
      - name: istio-proxy
        enabled: false

      - name: "*"
        controlledValues: RequestsOnly
      - name: my-app
        maxAllowed:
          memory: 8Gi          # controlledValues is NOT inherited - repeat it if you want it

  objectives:
    # Recommended: scale on the application container's CPU
    - type: ContainerResource
      containerResource:
        container: my-app
        name: cpu
        value:
          type: Utilization
          utilization: 65

  objectives:
    # Risky when sidecars are present: pod-level utilization is diluted by
    # sidecar requests, so a busy application container can appear idle.
    - type: PodResource
      podResource:
        name: cpu
        value:
          type: Utilization
          utilization: 65

apiVersion: apps/v1
kind: Deployment
metadata:
  name: my-app
spec:
  template:
    spec:
      initContainers:
        - name: log-shipper
          image: log-shipper:1.2
          restartPolicy: Always      # this is what makes it a native sidecar
          resources:
            requests: {cpu: 100m, memory: 128Mi}
            limits:   {memory: 256Mi}
      containers:
        - name: my-app
          image: my-app:4.5
          resources:
            requests: {cpu: "1", memory: 2Gi}
            limits:   {cpu: "2", memory: 4Gi}

spec:
  constraints:
    containers:
      - name: my-app
        controlledResources: [cpu, memory]
        controlledValues: RequestsAndLimits
      - name: log-shipper        # native sidecar, referenced by name
        enabled: false

spec:
  applyPolicy:
    mode: Preview     # recommendations are computed and visible in .status, but nothing is applied

spec:
  applyPolicy:
    scaleUp:
      strategy: Max
    scaleDown:
      strategy: Disabled     # never scale down
    update:
      strategy: Auto

spec:
  applyPolicy:
    update:
      strategy: Auto
      resizePendingPeriod: 600      # 1..3600 seconds
      rolloutFallbackDelay: 900     # 1..3600 seconds

spec:
  fallback:
    horizontal:
      enabled: true
      direction: ScaleUp          # default; use All to allow fallback scale-in as well
      triggers:
        staleRecommendationThresholdSeconds: 600    # 100..3600

  objectives:
    - type: ContainerResource
      containerResource:
        container: my-app
        name: cpu
        value:
          type: AbsoluteValue
          absoluteValue: "1.5"     # target cores per pod

  objectives:
    - type: CustomQuery
      customQuery:
        window: 5m
        request:
          queries:
            - name: a
              source: Metrics
              metrics:
                query: "avg:my.queue.depth{service:my-app}"
        value:
          type: AbsoluteValue
          absoluteValue: "100"

metadata:
  annotations:
    ad.datadoghq.com/tags: '{"team": "my-team", "tier": "critical"}'