[gcp] Migrate some gcp beat metricset to data streams

packages/gcp/_dev/build/docs/README.md

@@ -207,3 +207,29 @@ The `dns` dataset collects queries that name servers resolve for your Virtual Pr
 {{fields "dns"}}
 
 {{event "dns"}}
+
+## Metrics
+
+### Billing
+
+The `billing` dataset collects GCP Billing information from Google Cloud BigQuery daily cost detail table.
+
+{{fields "billing"}}
+
+{{event "billing"}}
+
+### Compute
+
+The `compute` dataset is designed to fetch metrics for [Compute Engine](https://cloud.google.com/compute/) Virtual Machines in Google Cloud Platform.
+
+{{fields "compute"}}
+
+{{event "compute"}}
+
+### Firestore
+
+The `firestore` dataset fetches metrics from [Firestore](https://cloud.google.com/firestore/) in Google Cloud Platform.
+
+{{fields "firestore"}}
+
+{{event "firestore"}}

packages/gcp/_dev/build/docs/billing.md

@@ -0,0 +1,17 @@
+# Billing
+
+## Metrics
+
+The `billing` dataset collects [Cloud Billing Reports](https://cloud.google.com/billing/docs/reports) information from Google Cloud BigQuery daily cost detail table. BigQuery is a fully-managed, serverless data warehouse. Cloud Billing export to BigQuery enables you to export detailed Google Cloud billing data (such as usage, cost estimates, and pricing data) automatically throughout the day to a BigQuery dataset that you specify. Then you can access your Cloud Billing data from BigQuery for detailed analysis.
+
+Please see [export cloud billing data to BigQuery](https://cloud.google.com/billing/docs/how-to/export-data-bigquery) for more details on how to export billing data.
+
+In BigQuery dataset, detailed Google Cloud daily cost data is loaded into a data table named `gcp_billing_export_v1_<BILLING_ACCOUNT_ID>`. There is a defined schema for Google Cloud daily cost data that is exported to BigQuery. Please see [daily cost detail data schema](https://cloud.google.com/billing/docs/how-to/export-data-bigquery-tables#data-schema) for more details.
+
+## Sample Event
+
+{{event "billing"}}
+
+## Exported fields
+
+{{fields "billing"}}

packages/gcp/_dev/build/docs/compute.md

@@ -0,0 +1,15 @@
+# Compute
+
+## Metrics
+
+The `compute` dataset is designed to fetch metrics for [Compute Engine](https://cloud.google.com/compute/) Virtual Machines in Google Cloud Platform. It contains all metrics exported from the [GCP Cloud Monitoring API](https://cloud.google.com/monitoring/api/metrics_gcp#gcp-compute).
+
+Extra labels and metadata are also extracted using the [Compute API](https://cloud.google.com/compute/docs/reference/rest/v1/instances/get). This is enough to get most of the info associated with a metric like Compute labels and metadata and metric specific Labels.
+
+## Sample Event
+
+{{event "compute"}}
+
+## Exported fields
+
+{{fields "compute"}}

packages/gcp/_dev/build/docs/firestore.md

@@ -0,0 +1,15 @@
+# Firestore
+
+## Metrics
+
+The `firestore` dataset fetches metrics from [Firestore](https://cloud.google.com/firestore/) in Google Cloud Platform. It contains all metrics exported from the [GCP Firestore Monitoring API](https://cloud.google.com/monitoring/api/metrics_gcp#gcp-firestore).
+
+You can specify a single region to fetch metrics like `us-central1`. Be aware that GCP Storage does not use zones so `us-central1-a` will return nothing. If no region is specified, it will return metrics from all buckets.
+
+## Sample Event
+
+{{event "firestore"}}
+
+## Exported fields
+
+{{fields "firestore"}}

packages/gcp/changelog.yml

@@ -1,4 +1,27 @@
 # newer versions go on top
+- version: 2.0.0
+  changes:
+    - description: |
+        Move configurations to support metrics. This change is breaking, as it moves
+        some configuration from the top level variables to data stream variables.
+
+        This change involves `project_id`, `credentials_file` and `credentials_json`
+        variables that are moved from input level configuration to package level
+        configuration (as those variables are reused across all inputs/data streams).
+
+        Users with GCP integration enabled will need to input values for these
+        variables again when upgrading the policies to this version.
+      type: breaking-change
+      link: https://github.com/elastic/integrations/pull/2707
+    - description: Add GCP Billing Data Stream
+      type: enhancement
+      link: https://github.com/elastic/integrations/pull/2141
+    - description: Add GCP Compute Data Stream
+      type: enhancement
+      link: https://github.com/elastic/integrations/pull/2301
+    - description: Add GCP Firestore Data stream
+      type: enhancement
+      link: https://github.com/elastic/integrations/pull/2704
 - version: "1.10.0"
   changes:
     - description: Update package to ECS 8.3.0.

packages/gcp/data_stream/audit/_dev/test/system/test-pubsub-config.yml

@@ -1,7 +1,6 @@
 service: gcppubsub-emulator
 input: gcp-pubsub
 vars:
-  alternative_host: "{{Hostname}}:{{Port}}"
   credentials_json: |-
     {
         "type": "service_account",
@@ -18,5 +17,6 @@ vars:
   project_id: audit
 data_stream:
   vars:
+    alternative_host: "{{Hostname}}:{{Port}}"
     subscription_name: subscription
     topic: topic

packages/gcp/data_stream/audit/manifest.yml

@@ -27,6 +27,13 @@ streams:
         required: true
         show_user: false
         default: false
+      - name: alternative_host
+        type: text
+        title: Alternative host
+        multi: false
+        required: false
+        show_user: false
+        description: "Overrides the default Pub/Sub service address and disables TLS. For testing."
       - name: tags
         type: text
         title: Tags

packages/gcp/data_stream/billing/agent/stream/stream.yml.hbs

@@ -0,0 +1,12 @@
+metricsets: ["billing"]
+period: {{period}}
+project_id: {{project_id}}
+{{#if credentials_file}}
+credentials_file_path: {{credentials_file}}
+{{/if}}
+{{#if credentials_json}}
+credentials_json: '{{credentials_json}}'
+{{/if}}
+dataset_id: {{dataset_id}}
+table_pattern: {{table_pattern}}
+cost_type: {{cost_type}}

packages/gcp/data_stream/billing/fields/agent.yml

@@ -0,0 +1,198 @@
+- name: cloud
+  title: Cloud
+  group: 2
+  description: Fields related to the cloud or infrastructure the events are coming from.
+  footnote: 'Examples: If Metricbeat is running on an EC2 host and fetches data from its host, the cloud info contains the data about this machine. If Metricbeat runs on a remote machine outside the cloud and fetches data from a service running in the cloud, the field contains cloud data from the machine the service is running on.'
+  type: group
+  fields:
+    - name: account.id
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: 'The cloud account or organization id used to identify different entities in a multi-tenant environment.
+
+        Examples: AWS account id, Google Cloud ORG Id, or other unique identifier.'
+      example: 666777888999
+    - name: availability_zone
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Availability zone in which this host is running.
+      example: us-east-1c
+    - name: instance.id
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Instance ID of the host machine.
+      example: i-1234567890abcdef0
+    - name: instance.name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Instance name of the host machine.
+    - name: machine.type
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Machine type of the host machine.
+      example: t2.medium
+    - name: provider
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Name of the cloud provider. Example values are aws, azure, gcp, or digitalocean.
+      example: aws
+    - name: region
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Region in which this host is running.
+      example: us-east-1
+    - name: project.id
+      type: keyword
+      description: Name of the project in Google Cloud.
+    - name: image.id
+      type: keyword
+      description: Image ID for the cloud instance.
+- name: container
+  title: Container
+  group: 2
+  description: 'Container fields are used for meta information about the specific container that is the source of information.
+
+    These fields help correlate data based containers from any runtime.'
+  type: group
+  fields:
+    - name: id
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: Unique container id.
+    - name: image.name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Name of the image the container was built on.
+    - name: labels
+      level: extended
+      type: object
+      object_type: keyword
+      description: Image labels.
+    - name: name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Container name.
+- name: host
+  title: Host
+  group: 2
+  description: 'A host is defined as a general computing instance.
+
+    ECS host.* fields should be populated with details about the host on which the event happened, or from which the measurement was taken. Host types include hardware, virtual machines, Docker containers, and Kubernetes nodes.'
+  type: group
+  fields:
+    - name: architecture
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: Operating system architecture.
+      example: x86_64
+    - name: domain
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: 'Name of the domain of which the host is a member.
+
+        For example, on Windows this could be the host''s Active Directory domain or NetBIOS domain name. For Linux this could be the domain of the host''s LDAP provider.'
+      example: CONTOSO
+      default_field: false
+    - name: hostname
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Hostname of the host.
+
+        It normally contains what the `hostname` command returns on the host machine.'
+    - name: id
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Unique host id.
+
+        As hostname is not always unique, use values that are meaningful in your environment.
+
+        Example: The current usage of `beat.name`.'
+    - name: ip
+      level: core
+      type: ip
+      description: Host ip addresses.
+    - name: mac
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: Host mac addresses.
+    - name: name
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Name of the host.
+
+        It can contain what `hostname` returns on Unix systems, the fully qualified domain name, or a name specified by the user. The sender decides which value to use.'
+    - name: os.family
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: OS family (such as redhat, debian, freebsd, windows).
+      example: debian
+    - name: os.kernel
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Operating system kernel version as a raw string.
+      example: 4.4.0-112-generic
+    - name: os.name
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      multi_fields:
+        - name: text
+          type: text
+          norms: false
+          default_field: false
+      description: Operating system name, without the version.
+      example: Mac OS X
+    - name: os.platform
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Operating system platform (such centos, ubuntu, windows).
+      example: darwin
+    - name: os.version
+      level: extended
+      type: keyword
+      ignore_above: 1024
+      description: Operating system version as a raw string.
+      example: 10.14.1
+    - name: type
+      level: core
+      type: keyword
+      ignore_above: 1024
+      description: 'Type of host.
+
+        For Cloud providers this can be the machine type like `t2.medium`. If vm, this could be the container, for example, or other information meaningful in your environment.'
+    - name: containerized
+      type: boolean
+      description: >
+        If the host is a container.
+
+    - name: os.build
+      type: keyword
+      example: "18D109"
+      description: >
+        OS build information.
+
+    - name: os.codename
+      type: keyword
+      example: "stretch"
+      description: >
+        OS codename, if any.
+

packages/gcp/data_stream/billing/fields/base-fields.yml

@@ -0,0 +1,20 @@
+- name: data_stream.type
+  type: constant_keyword
+  description: Data stream type.
+- name: data_stream.dataset
+  type: constant_keyword
+  description: Data stream dataset.
+- name: data_stream.namespace
+  type: constant_keyword
+  description: Data stream namespace.
+- name: '@timestamp'
+  type: date
+  description: Event timestamp.
+- name: event.module
+  type: constant_keyword
+  description: Event module
+  value: gcp
+- name: event.dataset
+  type: constant_keyword
+  description: Event dataset
+  value: gcp.billing

packages/gcp/data_stream/billing/fields/ecs.yml

@@ -0,0 +1,24 @@
+- external: ecs
+  name: cloud
+- external: ecs
+  name: cloud.account.id
+- external: ecs
+  name: cloud.account.name
+- external: ecs
+  name: cloud.availability_zone
+- external: ecs
+  name: cloud.instance.id
+- external: ecs
+  name: cloud.machine.type
+- external: ecs
+  name: cloud.provider
+- external: ecs
+  name: cloud.region
+- external: ecs
+  name: ecs.version
+- external: ecs
+  name: error
+- external: ecs
+  name: error.message
+- external: ecs
+  name: service.type