mmv1/products/compute/Autoscaler.yaml

# Copyright 2024 Google Inc.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

---
name: 'Autoscaler'
api_variant_patterns:
  - 'projects/{project}/zones/{zone}/autoscalers/{autoscaler}'
kind: 'compute#autoscaler'
description: |
  Represents an Autoscaler resource.

  Autoscalers allow you to automatically scale virtual machine instances in
  managed instance groups according to an autoscaling policy that you
  define.
references:
  guides:
    'Autoscaling Groups of Instances': 'https://cloud.google.com/compute/docs/autoscaler/'
  api: 'https://cloud.google.com/compute/docs/reference/rest/v1/autoscalers'
docs:
base_url: 'projects/{{project}}/zones/{{zone}}/autoscalers'
has_self_link: true
update_url: 'projects/{{project}}/zones/{{zone}}/autoscalers?autoscaler={{name}}'
timeouts:
  insert_minutes: 20
  update_minutes: 20
  delete_minutes: 20
async:
  actions: ['create', 'delete', 'update']
  type: 'OpAsync'
  operation:
    base_url: '{{op_id}}'
  result:
    resource_inside_response: false
collection_url_key: 'items'
custom_code:
sweeper:
  url_substitutions:
    - zone: "us-central1-a"
    - zone: "us-central1-f"
examples:
  - name: 'autoscaler_single_instance'
    primary_resource_id: 'default'
    min_version: 'beta'
    vars:
      autoscaler_name: 'my-autoscaler'
      instance_template_name: 'my-instance-template'
      target_pool_name: 'my-target-pool'
      igm_name: 'my-igm'
        # Add test_vars_overrides and oics_vars_overrides to fix the failing test,
        # which is caused by upgradting terraform-plugin-sdk to 2.24.0.
      provider_name: 'google-beta'
      provider_alias: ''
    test_vars_overrides:
      'provider_name': '"google-beta.us-central1"'
      'provider_alias': '"alias  = \"us-central1\""'
    oics_vars_overrides:
      'provider_name': 'google-beta'
      'provider_alias': ''
  - name: 'autoscaler_basic'
    primary_resource_id: 'foobar'
    vars:
      autoscaler_name: 'my-autoscaler'
      instance_template_name: 'my-instance-template'
      target_pool_name: 'my-target-pool'
      igm_name: 'my-igm'
parameters:
  - name: 'zone'
    type: ResourceRef
    description: |
      URL of the zone where the instance group resides.
    required: false
    immutable: true
    ignore_read: true
    default_from_api: true
    custom_expand: 'templates/terraform/custom_expand/resourceref_with_validation.go.tmpl'
    resource: 'Zone'
    imports: 'name'
properties:
  - name: 'creationTimestamp'
    type: Time
    description: 'Creation timestamp in RFC3339 text format.'
    output: true
  - name: 'name'
    type: String
    description: |
      Name of the resource. The name must be 1-63 characters long and match
      the regular expression `[a-z]([-a-z0-9]*[a-z0-9])?` which means the
      first character must be a lowercase letter, and all following
      characters must be a dash, lowercase letter, or digit, except the last
      character, which cannot be a dash.
    required: true
    immutable: true
    validation:
      function: 'verify.ValidateGCEName'
  - name: 'description'
    type: String
    description: |
      An optional description of this resource.
  - name: 'autoscalingPolicy'
    type: NestedObject
    description: |
      The configuration parameters for the autoscaling algorithm. You can
      define one or more of the policies for an autoscaler: cpuUtilization,
      customMetricUtilizations, and loadBalancingUtilization.

      If none of these are specified, the default will be to autoscale based
      on cpuUtilization to 0.6 or 60%.
    required: true
    properties:
      - name: 'minReplicas'
        type: Integer
        description: |
          The minimum number of replicas that the autoscaler can scale down
          to. This cannot be less than 0. If not provided, autoscaler will
          choose a default value depending on maximum number of instances
          allowed.
        api_name: minNumReplicas
        required: true
        send_empty_value: true
      - name: 'maxReplicas'
        type: Integer
        description: |
          The maximum number of instances that the autoscaler can scale up
          to. This is required when creating or updating an autoscaler. The
          maximum number of replicas should not be lower than minimal number
          of replicas.
        api_name: maxNumReplicas
        required: true
        send_empty_value: true
      - name: 'cooldownPeriod'
        type: Integer
        description: |
          The number of seconds that the autoscaler should wait before it
          starts collecting information from a new instance. This prevents
          the autoscaler from collecting information when the instance is
          initializing, during which the collected usage would not be
          reliable. The default time autoscaler waits is 60 seconds.

          Virtual machine initialization times might vary because of
          numerous factors. We recommend that you test how long an
          instance may take to initialize. To do this, create an instance
          and time the startup process.
        api_name: coolDownPeriodSec
        default_value: 60
      - name: 'mode'
        type: String
        description: |
          Defines operating mode for this policy.
        default_value: "ON"
      - name: 'scaleDownControl'
        type: NestedObject
        description: |
          Defines scale down controls to reduce the risk of response latency
          and outages due to abrupt scale-in events
        min_version: 'beta'
        required: false
        default_from_api: true
        properties:
          - name: 'maxScaledDownReplicas'
            type: NestedObject
            at_least_one_of:
              - 'autoscaling_policy.0.scale_down_control.0.max_scaled_down_replicas'
              - 'autoscaling_policy.0.scale_down_control.0.time_window_sec'
            properties:
              - name: 'fixed'
                type: Integer
                description: |
                  Specifies a fixed number of VM instances. This must be a positive
                  integer.
                at_least_one_of:
                  - 'autoscaling_policy.0.scale_down_control.0.max_scaled_down_replicas.0.fixed'
                  - 'autoscaling_policy.0.scale_down_control.0.max_scaled_down_replicas.0.percent'
              - name: 'percent'
                type: Integer
                description: |
                  Specifies a percentage of instances between 0 to 100%, inclusive.
                  For example, specify 80 for 80%.
                at_least_one_of:
                  - 'autoscaling_policy.0.scale_down_control.0.max_scaled_down_replicas.0.fixed'
                  - 'autoscaling_policy.0.scale_down_control.0.max_scaled_down_replicas.0.percent'
          - name: 'timeWindowSec'
            type: Integer
            description: |
              How long back autoscaling should look when computing recommendations
              to include directives regarding slower scale down, as described above.
            at_least_one_of:
              - 'autoscaling_policy.0.scale_down_control.0.max_scaled_down_replicas'
              - 'autoscaling_policy.0.scale_down_control.0.time_window_sec'
      - name: 'scaleInControl'
        type: NestedObject
        description: |
          Defines scale in controls to reduce the risk of response latency
          and outages due to abrupt scale-in events
        properties:
          - name: 'maxScaledInReplicas'
            type: NestedObject
            at_least_one_of:
              - 'autoscaling_policy.0.scale_in_control.0.max_scaled_in_replicas'
              - 'autoscaling_policy.0.scale_in_control.0.time_window_sec'
            properties:
              - name: 'fixed'
                type: Integer
                description: |
                  Specifies a fixed number of VM instances. This must be a positive
                  integer.
                at_least_one_of:
                  - 'autoscaling_policy.0.scale_in_control.0.max_scaled_in_replicas.0.fixed'
                  - 'autoscaling_policy.0.scale_in_control.0.max_scaled_in_replicas.0.percent'
              - name: 'percent'
                type: Integer
                description: |
                  Specifies a percentage of instances between 0 to 100%, inclusive.
                  For example, specify 80 for 80%.
                at_least_one_of:
                  - 'autoscaling_policy.0.scale_in_control.0.max_scaled_in_replicas.0.fixed'
                  - 'autoscaling_policy.0.scale_in_control.0.max_scaled_in_replicas.0.percent'
          - name: 'timeWindowSec'
            type: Integer
            description: |
              How long back autoscaling should look when computing recommendations
              to include directives regarding slower scale down, as described above.
            at_least_one_of:
              - 'autoscaling_policy.0.scale_in_control.0.max_scaled_in_replicas'
              - 'autoscaling_policy.0.scale_in_control.0.time_window_sec'
      - name: 'cpuUtilization'
        type: NestedObject
        description: |
          Defines the CPU utilization policy that allows the autoscaler to
          scale based on the average CPU utilization of a managed instance
          group.
        default_from_api: true
        properties:
          - name: 'target'
            type: Double
            description: |
              The target CPU utilization that the autoscaler should maintain.
              Must be a float value in the range (0, 1]. If not specified, the
              default is 0.6.

              If the CPU level is below the target utilization, the autoscaler
              scales down the number of instances until it reaches the minimum
              number of instances you specified or until the average CPU of
              your instances reaches the target utilization.

              If the average CPU is above the target utilization, the autoscaler
              scales up until it reaches the maximum number of instances you
              specified or until the average utilization reaches the target
              utilization.
            api_name: utilizationTarget
            required: true
          - name: 'predictiveMethod'
            type: String
            description: |
              Indicates whether predictive autoscaling based on CPU metric is enabled. Valid values are:

              - NONE (default). No predictive method is used. The autoscaler scales the group to meet current demand based on real-time metrics.

              - OPTIMIZE_AVAILABILITY. Predictive autoscaling improves availability by monitoring daily and weekly load patterns and scaling out ahead of anticipated demand.
            custom_flatten: 'templates/terraform/custom_flatten/default_if_empty.tmpl'
            default_value: "NONE"
      - name: 'metric'
        type: Array
        description: |
          Configuration parameters of autoscaling based on a custom metric.
        api_name: customMetricUtilizations
        item_type:
          type: NestedObject
          properties:
            - name: 'name'
              type: String
              description: |
                The identifier (type) of the Stackdriver Monitoring metric.
                The metric cannot have negative values.

                The metric must have a value type of INT64 or DOUBLE.
              api_name: metric
              required: true
            - name: 'singleInstanceAssignment'
              type: Double
              description: |
                If scaling is based on a per-group metric value that represents the
                total amount of work to be done or resource usage, set this value to
                an amount assigned for a single instance of the scaled group.
                The autoscaler will keep the number of instances proportional to the
                value of this metric, the metric itself should not change value due
                to group resizing.

                For example, a good metric to use with the target is
                `pubsub.googleapis.com/subscription/num_undelivered_messages`
                or a custom metric exporting the total number of requests coming to
                your instances.

                A bad example would be a metric exporting an average or median
                latency, since this value can't include a chunk assignable to a
                single instance, it could be better used with utilization_target
                instead.
            - name: 'target'
              type: Double
              description: |
                The target value of the metric that autoscaler should
                maintain. This must be a positive value. A utilization
                metric scales number of virtual machines handling requests
                to increase or decrease proportionally to the metric.

                For example, a good metric to use as a utilizationTarget is
                www.googleapis.com/compute/instance/network/received_bytes_count.
                The autoscaler will work to keep this value constant for each
                of the instances.
              api_name: utilizationTarget
            - name: 'type'
              type: Enum
              description: |
                Defines how target utilization value is expressed for a
                Stackdriver Monitoring metric.
              api_name: utilizationTargetType
              enum_values:
                - 'GAUGE'
                - 'DELTA_PER_SECOND'
                - 'DELTA_PER_MINUTE'
            - name: 'filter'
              type: String
              description: |
                A filter string to be used as the filter string for
                a Stackdriver Monitoring TimeSeries.list API call.
                This filter is used to select a specific TimeSeries for
                the purpose of autoscaling and to determine whether the metric
                is exporting per-instance or per-group data.

                You can only use the AND operator for joining selectors.
                You can only use direct equality comparison operator (=) without
                any functions for each selector.
                You can specify the metric in both the filter string and in the
                metric field. However, if specified in both places, the metric must
                be identical.

                The monitored resource type determines what kind of values are
                expected for the metric. If it is a gce_instance, the autoscaler
                expects the metric to include a separate TimeSeries for each
                instance in a group. In such a case, you cannot filter on resource
                labels.

                If the resource type is any other value, the autoscaler expects
                this metric to contain values that apply to the entire autoscaled
                instance group and resource label filtering can be performed to
                point autoscaler at the correct TimeSeries to scale upon.
                This is called a per-group metric for the purpose of autoscaling.

                If not specified, the type defaults to gce_instance.

                You should provide a filter that is selective enough to pick just
                one TimeSeries for the autoscaled group or for each of the instances
                (if you are using gce_instance resource type). If multiple
                TimeSeries are returned upon the query execution, the autoscaler
                will sum their respective values to obtain its scaling value.
              default_value: "resource.type = gce_instance"
      - name: 'loadBalancingUtilization'
        type: NestedObject
        description: |
          Configuration parameters of autoscaling based on a load balancer.
        properties:
          - name: 'target'
            type: Double
            description: |
              Fraction of backend capacity utilization (set in HTTP(s) load
              balancing configuration) that autoscaler should maintain. Must
              be a positive float value. If not defined, the default is 0.8.
            api_name: utilizationTarget
            required: true
      - name: 'scalingSchedules'
        type: Map
        description: |
          Scaling schedules defined for an autoscaler. Multiple schedules can be set on an autoscaler and they can overlap.
        key_name: 'name'
        key_description: |
          A name for the schedule.
        value_type:
          name: scalingSchedule
          type: NestedObject
          properties:
            - name: 'minRequiredReplicas'
              type: Integer
              description: |
                Minimum number of VM instances that autoscaler will recommend in time intervals starting according to schedule.
              required: true
              send_empty_value: true
            - name: 'schedule'
              type: String
              description: |
                The start timestamps of time intervals when this scaling schedule should provide a scaling signal. This field uses the extended cron format (with an optional year field).
              required: true
            - name: 'timeZone'
              type: String
              description: |
                The time zone to be used when interpreting the schedule. The value of this field must be a time zone name from the tz database: http://en.wikipedia.org/wiki/Tz_database.
              default_value: "UTC"
            - name: 'durationSec'
              type: Integer
              description: |
                The duration of time intervals (in seconds) for which this scaling schedule will be running. The minimum allowed value is 300.
              required: true
            - name: 'disabled'
              type: Boolean
              description: |
                A boolean value that specifies if a scaling schedule can influence autoscaler recommendations. If set to true, then a scaling schedule has no effect.
              default_value: false
            - name: 'description'
              type: String
              description: |
                A description of a scaling schedule.
  - name: 'target'
    type: ResourceRef
    description: |
      URL of the managed instance group that this autoscaler will scale.
    required: true
    custom_expand: 'templates/terraform/custom_expand/compute_full_url.tmpl'
    resource: 'InstanceGroupManager'
    imports: 'selfLink'