spec.yaml

name: Postgres
fleet_configurable: true
files:
- name: postgres.yaml
  options:
  - template: init_config
    options:
    - name: propagate_agent_tags
      display_priority: 0
      description: |
        Set to `true` to propagate the tags from `datadog.yaml` and the agent host tags to the check.
        When set to `true`, the tags from the agent host are added to the check's tags for all instances.
      fleet_configurable: true
      value:
        example: false
        type: boolean
    - template: init_config/db
    - template: init_config/default
  - template: instances
    options:
    - name: host
      display_priority: 24
      description: |
        The hostname to connect to. To connect to a Unix socket, specify the full path to the socket directory,
        e.g. `/var/run/postgresql`.
      fleet_configurable: true
      value:
        type: string
        display_default: "localhost"
    - name: port
      display_priority: 23
      description: The port to use when connecting to PostgreSQL.
      fleet_configurable: true
      value:
        type: integer
        display_default: 5432
    - name: username
      display_priority: 22
      description: The Datadog username created to connect to PostgreSQL.
      fleet_configurable: true
      value:
        type: string
        display_default: "datadog"
    - name: password
      display_priority: 21
      description: The password associated with the Datadog user.
      fleet_configurable: true
      secret: true
      value:
        type: string
    - name: dbname
      display_priority: 0
      description: |
        The name of the PostgreSQL database to monitor.
        Note: If omitted, the default system Postgres database is queried.
      fleet_configurable: true
      value:
        type: string
        display_default: postgres
    - name: dbm
      display_priority: 0
      fleet_configurable: true
      description: |
        Set to `true` to enable Database Monitoring.
      value:
        type: boolean
        example: false
        display_default: false
    - name: relations
      display_priority: 0
      fleet_configurable: true
      description: |
        The list of relations/tables must be specified here to track per-relation (table, index, view, etc.) metrics.
        If enabled, `dbname` should be specified to collect database-specific relations metrics.
        You can either specify a single relation by its exact name in 'relation_name' or use a regex to track metrics
        from all matching relations (useful in cases where relation names are dynamically generated, e.g. TimescaleDB).
        Each relation generates many metrics (dozens per relation, plus several more for each index).
        Be mindful of the metric volume this can produce: on large instances, broad `relation_regex`
        patterns that match many relations can emit metrics in the thousands.

        By default all schemas are included. To track relations from specific schemas only,
        you can specify the `schemas` attribute and provide a list of schemas to use for filtering.

        Size metrics are collected only for ordinary tables. Index metrics are collected only for user indexes. Lock
        metrics are collected for all relation types (table, index , view, etc.). The rest of the metrics are
        collected only for user tables.
        To track lock metrics for relations of a specific kind only, specify the `relkind` attribute
        as a list of the options:
        * r = ordinary table
        * i = index
        * S = sequence
        * t = TOAST table
        * m = materialized view
        * c = composite type
        * f = foreign table
        * p = partitioned table

        Note: For compatibility reasons you can also use the following syntax to track relations metrics by specifying
        the list of table names. All schemas are included.
        relations:
      value:
        type: array
        items:
          anyOf:
          - type: string
          - type: object
            properties:
              - name: relation_name
                type: string
              - name: relation_schema
                type: string
              - name: schemas
                type: array
                items:
                  type: string
              - name: relation_regex
                type: string
              - name: relkind
                type: array
                items:
                    type: string
        default: []
        example:
          - relation_name: <TABLE_NAME>
            schemas:
              - <SCHEMA_NAME1>
          - relation_regex: <TABLE_PATTERN>
            relkind:
              - r
              - p
    - name: collect_activity_metrics
      display_priority: 0
      fleet_configurable: true
      description: |
        Collect metrics regarding transactions from pg_stat_activity. Please make sure the user
        has sufficient privileges to read from pg_stat_activity before enabling this option.
      value:
        type: boolean
        example: false
    - name: collect_function_metrics
      display_priority: 0
      fleet_configurable: true
      description: |
        If set to true, collects metrics regarding PL/pgSQL functions from pg_stat_user_functions.
      value:
        type: boolean
        example: false
    - name: collect_database_size_metrics
      display_priority: 0
      fleet_configurable: true
      description: Collect database size metrics.
      value:
        type: boolean
        example: true
    - name: collect_bloat_metrics
      display_priority: 0
      fleet_configurable: true
      description: Collect metrics about table bloat. Only available when `relation` metrics are enabled.
      enabled: true
      value:
        type: boolean
        example: false
    - name: tag_replication_role
      display_priority: 0
      fleet_configurable: true
      hidden: true
      description: Tag metrics and checks with `replication_role:<master|standby>`.
      value:
        type: boolean
        example: true
    - name: collect_count_metrics
      display_priority: 0
      fleet_configurable: true
      description: Collect count of user tables from pg_class.
      value:
        type: boolean
        example: true
    - name: max_relations
      display_priority: 0
      fleet_configurable: true
      description: Determines the maximum number of relations to fetch.
      value:
        type: integer
        example: 300
    - name: ssl
      display_priority: 0
      description: |
        This option determines whether or not and with what priority a secure SSL TCP/IP connection
        is negotiated with the server.

        There are six modes:
        - `disable`: Only tries a non-SSL connection.
        - `allow`: First tries a non-SSL connection; if it fails, tries an SSL connection.
        - `prefer`: First tries an SSL connection; if it fails, tries a non-SSL connection.
        - `require`: Only tries an SSL connection. If a root CA file is present, verifies the certificate in
                     the same way as if verify-ca was specified.
        - `verify-ca`: Only tries an SSL connection, and verifies that the server certificate is issued by a
                       trusted certificate authority (CA).
        - `verify-full`: Only tries an SSL connection and verifies that the server certificate is issued by a
                         trusted CA and that the requested server host name matches the one in the certificate.

        For a detailed description of how these options work see https://www.postgresql.org/docs/current/libpq-ssl.html
      fleet_configurable: true
      value:
        type: string
        example: 'allow'
        default: 'allow'
    - name: collect_default_database
      display_priority: 0
      fleet_configurable: true
      description: Include statistics from the default database 'postgres' in the check metrics.
      value:
        type: boolean
        example: true
    - name: query_timeout
      display_priority: 0
      fleet_configurable: true
      description: |
        Adds a statement_timeout https://www.postgresql.org/docs/current/runtime-config-client.html#GUC-STATEMENT-TIMEOUT
        to all metric collection queries. Aborts any statement that takes more than the specified number of milliseconds,
        starting from the time the command arrives at the server from the client. A value of zero turns this off.
        Cancelled queries won't log any metrics.
      value:
        type: integer
        example: 5000
    - name: reported_hostname
      display_priority: 0
      description: |
        Set the reported hostname for this instance. This value overrides the hostname detected by the Agent
        and can be useful to set a custom hostname when connecting to a remote database through a proxy.
      fleet_configurable: true
      value:
        type: string
        default: null
    - name: ignore_databases
      display_priority: 0
      fleet_configurable: true
      description: |
        A list of databases to ignore. No metrics or statement samples will be collected for these databases.
        Each value can be a plain string or a Postgres pattern. If you want to ignore the postgres database,
        set collect_default_database to false in addition to adding it to this array.
        For more information on how patterns work, see https://www.postgresql.org/docs/12/functions-matching.html
      value:
        type: array
        items:
          type: string
        example:
          - 'template0'
          - 'template1'
          - rdsadmin
          - azure_maintenance
          - cloudsqladmin
          - alloydbadmin
          - alloydbmetadata
        default:
          - 'template0'
          - 'template1'
          - rdsadmin
          - azure_maintenance
          - cloudsqladmin
          - alloydbadmin
          - alloydbmetadata
    - name: exclude_hostname
      display_priority: 0
      description: |
        Omit the hostname from tags and events. This is useful when the database host is not monitored by an agent.
      value:
        type: boolean
        example: false
      fleet_configurable: false
    - name: database_identifier
      display_priority: 0
      description: |
        Controls how the database is identified. Each unique value of this identifier will appear in DBM as a separate
        billable instance.
        
        The default value is the resolved hostname for the instance, which respects the `reported_hostname` option.

        This value will be used as-is for the display name of the instance but will be normalized
        when applied as the `database_instance` tag. Please see https://docs.datadoghq.com/getting_started/tagging/
        for more details on Datadog tag normalization.
      options:
        - name: template
          value:
            type: string
            display_default: "$resolved_hostname"
            example: "$env-$resolved_hostname:$port"
          description: |
            The template to use for the database identifier. The default value is `$resolved_hostname`.
            You can use the following variables, prefixed by `$` in the template:
            - resolved_hostname: The resolved hostname of the instance, which respects the `reported_hostname` option.
            - host: The provided host of the instance.
            - port: The port number of the instance.
            In addition, you can use any key from the `tags` section of the configuration.
          fleet_configurable: false
    - name: dbstrict
      display_priority: 0
      fleet_configurable: true
      description: |
        Whether to restrict the scope of the check to just the database in question.
        Set to `true` if you only want to gather metrics from the database provided in the dbname parameter.
      value:
        type: boolean
        display_default: false
        example: false
    - name: ignore_schemas_owned_by
      display_priority: 0
      fleet_configurable: true
      description: |
        A list of database users which own schemas to ignore.
        No metrics will be collected for these schemas.
        Each value can be a plain string or a Postgres pattern.
      value:
        type: array
        items:
          type: string
        example:
          - rds_superuser
          - rdsadmin
          - user123
          - 'dev_%_owner'
        default:
          - rds_superuser
          - rdsadmin
    - name: ssl_root_cert
      display_priority: 0
      description: |
        The path to the ssl root certificate.

        For a detailed description of how this option works see https://www.postgresql.org/docs/current/libpq-ssl.html
      fleet_configurable: true
      value:
        type: string
        require_trusted_provider: true
        default: null
    - name: ssl_cert
      display_priority: 0
      description: |
        The path to the ssl certificate.

        For a detailed description of how this option works see https://www.postgresql.org/docs/current/libpq-ssl.html
      fleet_configurable: true
      value:
        type: string
        require_trusted_provider: true
        default: null
    - name: ssl_key
      display_priority: 0
      description: |
        The path to the ssl client key.

        For a detailed description of how this option works see https://www.postgresql.org/docs/current/libpq-ssl.html
      value:
        type: string
        require_trusted_provider: true
        default: null
      fleet_configurable: false
    - name: ssl_password
      display_priority: 0
      description: |
        The password for the secret key specified in ssl_key, allowing client certificate private keys to be stored
        in encrypted form on disk.

        For a detailed description of how this option works see https://www.postgresql.org/docs/current/libpq-ssl.html
      secret: true
      value:
        type: string
        default: null
      fleet_configurable: false
    - name: idle_connection_timeout
      display_priority: 0
      fleet_configurable: true
      description: |
        Sets the timeout (in ms) a connection used in the connection pool will be idle until it is closed by the pooler.
        This value should be configured to a lower value if you are observing connection buildup on the Postgres server,
        or a higher value if connections are getting prematurely closed.
      hidden: true
      value:
        type: integer
        example: 60000
    - name: max_connections
      display_priority: 0
      hidden: true
      description: |
        Sets the upper bound limit on the number of concurrent connections the Agent can have on the database server.
        The Agent needs to open additional connections to collect explain plans across databases.
        Idle connections are cached, but pruned over time to balance the performance impact of opening connections and the cost of having many open connections.
        Raising the default value should only be needed on workloads with >50 databases.
        Lowering the default value can reduce the number of explain plans collected and is not recommended in most cases.
      value:
        type: integer
        example: 30
        display_default: 30
      fleet_configurable: false
    - name: locks_idle_in_transaction
      display_priority: 0
      description: Configure collection of idle in transaction lock age metrics
      hidden: true
      options:
        - name: enabled
          description: Enable collection of idle in transaction lock age metrics.
          value:
            type: boolean
            example: true
            display_default: true
          hidden: true
          fleet_configurable: false
        - name: collection_interval
          description: Set the collection interval (in seconds) for idle in transaction lock age metrics.
          value:
            type: number
            example: 300
            display_default: 300
          hidden: true
          fleet_configurable: false
        - name: max_rows
          description: Set the maximum number of rows to collect per check run.
          value:
            type: integer
            example: 100
            display_default: 100
          hidden: true
          fleet_configurable: false
    - name: collect_checksum_metrics
      display_priority: 0
      fleet_configurable: true
      description: Collect counts of database failed checksums. Only supported on versions >= 12.
      value:
        type: boolean
        example: false
    - name: activity_metrics_excluded_aggregations
      display_priority: 0
      description: |
        A list of columns to remove from the pg_stat_activity aggregation.
        By default, datname, usename and application_name will be used.
        If applications with different application_name are creating a lot of short-lived queries,
        removing application_name from the aggregation can help generate more stable metrics.
        Note that datname is a required aggregation on activity metrics and can't be excluded.
      value:
        type: array
        items:
          type: string
        example:
          - application_name
        default: []
      fleet_configurable: false
    - name: collect_buffercache_metrics
      display_priority: 0
      fleet_configurable: true
      description: |
        If set to true, collects metrics regarding buffer cache usage from pg_buffercache.
        pg_buffercache extension must be installed.
      value:
        type: boolean
        example: false
    - name: collect_wal_metrics
      display_priority: 0
      fleet_configurable: true
      description: |
        Collect metrics about WAL file age.

        When unset, this defaults to `true` for Postgres 10+ (uses `pg_ls_waldir` via SQL) and `false` for
        Postgres 9.6 and below (requires local filesystem access to the WAL directory).

        Set to `true` explicitly for Postgres 9.6 and below only if the Agent runs on the same host as the
        database and has read access to the WAL directory. You must also configure `data_directory`.
      value:
        type: boolean
        example: true
        display_default: null
    - name: data_directory
      display_priority: 0
      description: |
        The data directory of your postgres installation.
        Only used when `collect_wal_metrics` is explicitly set to `true` on Postgres 9.6 and below.
      value:
        type: string
        example: /usr/local/pgsql/data
        display_default: /usr/local/pgsql/data
      fleet_configurable: false
    - name: table_count_limit
      display_priority: 0
      fleet_configurable: true
      description: The maximum number of tables to collect metrics from.
      value:
        type: integer
        display_default: 200
    - name: custom_metrics
      display_priority: 0
      description: This option is deprecated. Use `custom_queries` instead.
      hidden: true
      value:
        type: array
        items:
          type: object
      fleet_configurable: false
    - name: database_autodiscovery
      display_priority: 0
      fleet_configurable: true
      description: |
        Define the configuration for database autodiscovery.
        Complete this section if you want to auto-discover databases on this host
        instead of specifying each using dbname.
      options:
        - name: enabled
          fleet_configurable: true
          description: Enable database autodiscovery.
          value:
            type: boolean
            example: false
            display_default: false
        - name: global_view_db
          fleet_configurable: true
          description: Database the agent connects to perform autodiscovery operations
          value:
            type: string
            example: postgres
            display_default: postgres
        - name: max_databases
          fleet_configurable: true
          description: The maximum number of databases this host should monitor.
          value:
            type: integer
            example: 100
            display_default: 100
        - name: include
          fleet_configurable: true
          description: |
            Regular expression for database names to include as part of
            database autodiscovery.
            Will report metrics for databases that are found in this instance,
            ignores databases listed but not found.
            Character casing is ignored. The regular expressions start matching from
            the beginning, so to match anywhere, prepend `.*`. For exact matches append `$`.
            Defaults to `.*` to include everything.
          value:
            type: array
            items:
              type: string
            example:
              - "master$"
              - "AdventureWorks.*"
            display_default:
              - ".*"
        - name: exclude
          fleet_configurable: true
          description: |
            Regular expression for database names to exclude as part of `database_autodiscovery`.
            Character casing is ignored. The regular expressions start matching from the beginning,
            so to match anywhere, prepend `.*`. For exact matches append `$`.
            In case of conflicts, database exclusion via `exclude` takes precedence over
            those found via `include`
          value:
            type: array
            items:
              type: string
            example:
              - "model"
              - "msdb"
              - "cloudsqladmin"
              - "rdsadmin"
            display_default:
              - "template0"
              - "template1"
              - "rdsadmin"
              - "azure_maintenance"
              - "cloudsqladmin"
              - "alloydbadmin"
              - "alloydbmetadata"
        - name: refresh
          description: Frequency in seconds of scans for new databases. Defaults to 10 minutes.
          value:
            type: integer
            example: 600
            display_default: 600
          fleet_configurable: false
    - name: application_name
      display_priority: 0
      fleet_configurable: true
      description: |
        The application_name can be any string of less than NAMEDATALEN characters (64 characters in a standard build).
        It is typically set by an application upon connection to the server.
        The name is displayed in the pg_stat_activity view and included in CSV log entries.
      value:
        type: string
        example: "datadog-agent"
    - name: data_observability
      display_priority: 0
      fleet_configurable: true
      description: |
        Configure the Data Observability async job, which executes monitoring
        queries delivered via Remote Configuration.
      options:
        - name: enabled
          fleet_configurable: true
          description: Enable the Data Observability job.
          value:
            type: boolean
            example: false
            display_default: false
        - name: collection_interval
          fleet_configurable: true
          description: |
            How often (in seconds) the job wakes up to check which queries are
            due. Individual queries have their own interval_seconds. This value
            must be less than or equal to the smallest interval_seconds across
            all configured queries (i.e. the least common denominator), otherwise
            queries with short intervals will be delayed.
          value:
            type: number
            example: 10
            display_default: 10
        - name: run_sync
          hidden: true
          description: Run the job synchronously (for testing).
          value:
            type: boolean
            example: false
            display_default: false
          fleet_configurable: false
        - name: config_id
          hidden: true
          description: |
            Unique identifier of the Remote Configuration payload that populated
            this data_observability block. Set automatically by the Datadog Agent
            Go RC handler when it delivers query configuration; do not set this
            field manually. It is forwarded as-is on every emitted event so that
            the intake can correlate results back to the originating RC config.
          value:
            type: string
          fleet_configurable: false
        - name: queries
          hidden: true
          description: |
            List of monitor queries to execute. Populated automatically by the
            Datadog Agent Go RC handler when Remote Configuration delivers a
            DO_QUERY_ACTIONS payload; do not set this field manually. Each entry
            describes one SQL monitoring query along with its scheduling
            parameters and entity metadata.
          value:
            type: array
            items:
              type: object
              required:
                - monitor_id
                - dbname
                - query
                - query_timeout
                - entity
              properties:
              - name: monitor_id
                type: integer
              - name: dbname
                type: string
              - name: type
                type: string
              - name: query
                type: string
              - name: interval_seconds
                description: |
                  How often (in seconds) to run this query. Ignored when schedule is set
                  (see schedule for the precedence rule).
                type: integer
              - name: schedule
                description: |
                  A standard 5-field cron expression (minute hour dom month dow) specifying
                  when to run this query. When both schedule and interval_seconds are set,
                  schedule wins and interval_seconds is ignored. If neither is set, the
                  query is skipped at runtime with a warning.
                type: string
              - name: query_timeout
                description: |
                  Statement timeout for this query in milliseconds. Overrides the instance-level
                  query_timeout for this query only.
                type: integer
              - name: entity
                type: object
                required:
                  - platform
                  - account
                  - database
                  - schema
                  - table
                properties:
                - name: platform
                  type: string
                - name: account
                  type: string
                - name: database
                  type: string
                - name: schema
                  type: string
                - name: table
                  type: string
              - name: custom_sql_select_fields
                type: object
                properties:
                - name: metric_config_id
                  type: integer
                - name: entity_id
                  type: string
          fleet_configurable: false
    - name: pg_stat_statements_view
      display_priority: 0
      description: |
        Set this value if you want to define a custom view or function to allow the datadog user to query the
        `pg_stat_statements` table, which is useful for restricting the permissions given to the datadog agent.
        Please note this is an ALPHA feature and is subject to change or deprecation without notice.
      value:
        type: string
        example: show_pg_stat_statements()
        display_default: pg_stat_statements
      fleet_configurable: false
    - name: pg_stat_activity_view
      display_priority: 0
      hidden: true
      description: |
        Set this value if you want to define a custom view or function to allow the datadog user to query the
        `pg_stat_activity` table, which is useful for restricting the permissions given to the datadog agent.
        Please note this is an ALPHA feature and is subject to change or deprecation without notice.
      value:
        type: string
        display_default: pg_stat_activity
      fleet_configurable: false
    - name: query_encodings
      display_priority: 0
      description: |
        Set this value if your database is encoded in SQL_ASCII and you have clients that use encodings other than UTF-8.
        When attempting to decode stored query text for query metrics, samples and activity, the agent will use these
        values in order and return the first successful decoding. Only supported for Postgres 10 and above.

        Note that the values should be the Python versions of the encoding names, which can be referenced at:
        https://docs.python.org/3/library/codecs.html#standard-encodings
      value:
        type: array
        items:
          type: string
        example:
          - utf8
          - latin1
        display_default:
          - utf8
      fleet_configurable: false
    - name: query_metrics
      display_priority: 0
      fleet_configurable: true
      description: Configure collection of query metrics
      options:
        - name: enabled
          fleet_configurable: true
          description: |
            Enable collection of query metrics. Requires `dbm: true`.
          value:
            type: boolean
            example: true
        - name: collection_interval
          fleet_configurable: true
          description: |
            Set the query metric collection interval (in seconds). Each collection involves a single query to
            `pg_stat_statements`. If a non-default value is chosen then that exact same value must be used for *every*
            check instance. Running different instances with different collection intervals is not supported.
          value:
            type: number
            example: 10
        - name: pg_stat_statements_max_warning_threshold
          hidden: true
          description: |
            Set the threshold for a safe value of `pg_stat_statements.max`. If the database is configured with a value
            higher than this threshold, a warning is emitted to recommend lowering the setting value.
          value:
            type: number
            default: 10000
          fleet_configurable: false
        - name: full_statement_text_cache_max_size
          hidden: true
          description: |
            Set the max size of the cache used for the full statement text.
          value:
            type: number
            default: 10000
          fleet_configurable: false
        - name: full_statement_text_samples_per_hour_per_query
          hidden: true
          description: |
            Set the max number of full statement text samples to collect per hour per query.
          value:
            type: number
            default: 1
          fleet_configurable: false
        - name: incremental_query_metrics
          hidden: true
          description: |
            When enabled query metrics collection uses a lightweight multi-pass pipeline.
            The check determines which statements had a change in call counts since the last collection, then fetches
            query text from `pg_stat_statements` and runs obfuscation for those statements.
          value:
            type: boolean
            display_default: true
            example: true
          fleet_configurable: false
        - name: run_sync
          hidden: true
          description: |
            Run the query metrics collection synchronously. This is useful for testing purposes, but should not be used
            in production as it can block the main thread and cause performance issues.
          value:
            type: boolean
            example: false
          fleet_configurable: false
        - name: batch_max_content_size
          hidden: true
          description: |
            This is a stub option for type hints. This value is actually set in the datadog.yaml config using
            database_monitoring.metrics.batch_max_content_size. For details on this parameter, see statements.py.
          value:
            type: integer
            example: 20_000_000
          fleet_configurable: false
    - name: query_samples
      display_priority: 0
      fleet_configurable: true
      description: Configure collection of explain plan samples
      options:
        - name: enabled
          fleet_configurable: true
          description: |
            Enable collection of explain plans. Requires `dbm: true`.
          value:
            type: boolean
            example: true
        - name: collection_interval
          fleet_configurable: true
          description: |
            Set the explain plan collection interval (in seconds). Each collection involves a single query to
            `pg_stat_activity` followed by at most one `EXPLAIN` query per unique normalized query seen.
          value:
            type: number
            example: 1
        - name: explain_function
          fleet_configurable: true
          description: |
            Override the default function used to collect explain plans for queries.
          value:
            type: string
            example: datadog.explain_statement
        - name: explained_queries_per_hour_per_query
          description: |
            Set the rate limit for how many explain plans will be collected per hour per normalized query.
          value:
            type: integer
            example: 60
          fleet_configurable: false
        - name: samples_per_hour_per_query
          description: |
            Set the rate limit for how many explain plan events will be ingested per hour per normalized explain
            plan.
          value:
            type: integer
            example: 15
          fleet_configurable: false
        - name: explained_queries_cache_maxsize
          description: |
            Set the max size of the cache used for the explained_queries_per_hour_per_query rate limit. This should
            be increased for databases with a very large number unique normalized queries which exceed the cache's
            limit.
          value:
            type: integer
            example: 5000
          fleet_configurable: false
        - name: seen_samples_cache_maxsize
          description: |
            Set the max size of the cache used for the samples_per_hour_per_query rate limit. This should be increased
            for databases with a very large number of unique normalized explain plans which exceed the cache's limit.
          value:
            type: integer
            example: 10000
          fleet_configurable: false
        - name: explain_parameterized_queries
          fleet_configurable: true
          description: |
            This option will enable the ability to explain parameterized queries.
            This is useful if your SQL clients are using the extended query protocol or prepared statements.
          value:
            type: boolean
            example: true
        - name: explain_errors_cache_maxsize
          hidden: true
          description: |
            Set the max size of the cache used for the explain errors.
          value:
            type: integer
            default: 5000
          fleet_configurable: false
        - name: explain_errors_cache_ttl
          hidden: true
          description: |
            Set the ttl in seconds of the cache used for the explain errors.
          value:
            type: integer
            default: 86400
          fleet_configurable: false
        - name: run_sync
          hidden: true
          description: |
            Run the query metrics collection synchronously. This is useful for testing purposes, but should not be used
            in production as it can block the main thread and cause performance issues.
          value:
            type: boolean
            example: false
          fleet_configurable: false
    - name: query_activity
      display_priority: 0
      fleet_configurable: true
      description: Configure collection of in-flight query samples
      options:
        - name: enabled
          fleet_configurable: true
          description: |
            Enable collection of in-flight query samples. Requires `dbm: true`.
          value:
            type: boolean
            example: true
        - name: collection_interval
          fleet_configurable: true
          description: |
            Set the in-flight query sample collection interval (in seconds). This number cannot be smaller than
            the `query_samples` configured collection_interval.
          value:
            type: number
            example: 10
          hidden: true
        - name: payload_row_limit
          fleet_configurable: true
          description: |
            Set the maximum number of pg_stat_activity rows you want to report. If the table is larger
            than the maximum rows set, then the top N longest running transactions will be reported.
          value:
            type: number
            example: 3500
    - name: collect_settings
      display_priority: 0
      fleet_configurable: true
      description: Configure collection of pg_settings.
      options:
        - name: enabled
          fleet_configurable: true
          description: |
            Enable collection of pg_settings. Requires `dbm: true`.
          value:
            type: boolean
            example: true
        - name: collection_interval
          fleet_configurable: true
          description: |
            Set the database settings collection interval (in seconds). Each collection involves a single query to
            `pg_settings`.
          value:
            type: number
            example: 600
        - name: ignored_settings_patterns
          fleet_configurable: true
          description: |
            A list of setting patterns to ignore. Any setting key matching one of the values in this list will
            not be collected. This uses the traditional LIKE pattern-matching approach.
          value:
              type: array
              items:
                type: string
              example:
                - plpgsql%
              default:
                - plpgsql%
        - name: run_sync
          fleet_configurable: true
          hidden: true
          description: |
            Run the metadata collection synchronously. This is useful for testing purposes, but should not be used
            in production as it can block the main thread and cause performance issues.
          value:
            type: boolean
            example: false
    - name: collect_schemas
      display_priority: 0
      fleet_configurable: true
      description: |
        Enable collection of database schemas. In order to collect schemas from all user databases,
        enable `database_autodiscovery`. To collect from a single database, set `dbname` to collect
        the schema for that database.
      options:
        - name: enabled
          fleet_configurable: true
          description: |
            Enable collection of database schemas. Requires `dbm: true`.
          value:
            type: boolean
            example: true
        - name: max_tables
          fleet_configurable: true
          description: |
            Maximum amount of tables the Agent collects from the instance.
          value:
            type: number
            example: 300
            display_default: 300
        - name: max_query_duration
          fleet_configurable: true
          description: |
            Maximum duration of the query to collect schema information in seconds.
          value:
            type: number
            display_default: 60
        - name: max_columns
          fleet_configurable: true
          description: |
            Maximum amount of columns the Agent collects per table.
          value:
            type: number
            example: 50
            display_default: 50
        - name: collection_interval
          fleet_configurable: true
          description: |
            The database schema collection interval (in seconds).
          value:
            type: number
            example: 600
        - name: include_databases
          fleet_configurable: true
          description: |
            A list of regex patterns to include databases. 
            Any database whose name matches any one of these patterns will be included. 
            If empty, all databases matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "mydb"
        - name: exclude_databases
          fleet_configurable: true
          description: |
            A list of regex patterns to exclude databases.
            Any database whose name matches any one of these patterns will be excluded.
            If empty, all databases matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "privatedb.*"
            default:
              - "template0"
              - "template1"
              - "rdsadmin"
              - "azure_maintenance"
              - "cloudsqladmin"
              - "alloydbadmin"
              - "alloydbmetadata"
        - name: include_schemas
          fleet_configurable: true
          description: |
            A list of regex patterns to include schemas. 
            Any schema whose name matches any one of these patterns will be included.
            If empty, all schemas matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "myschema"
        - name: exclude_schemas
          fleet_configurable: true
          description: |
            A list of regex patterns to exclude schemas. 
            Any schema whose name matches any one of these patterns will be excluded.
            If empty, all schemas matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "privateschema.*"
        - name: include_tables
          fleet_configurable: true
          description: |
            A list of regex patterns to include tables. 
            Any table whose name matches any one of these patterns will be included.
            If empty, all tables matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "users.*"
        - name: exclude_tables
          fleet_configurable: true
          description: |
            A list of regex patterns to exclude tables. 
            Any table whose name matches any one of these patterns will be excluded.
            If empty, all tables matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "customer.*"

    - name: collect_column_statistics
      description: |
        Enable collection of column statistics from pg_stats.
        Requires the `datadog.column_statistics()` function to be created in the database.
      options:
        - name: enabled
          description: |
            Enable collection of column statistics. Requires `dbm: true`.
          value:
            type: boolean
            example: false
          fleet_configurable: false
        - name: collection_interval
          description: |
            Set the column statistics collection interval (in seconds).
          value:
            type: number
            example: 3600
            display_default: 3600
          fleet_configurable: false
        - name: max_tables
          description: |
            Maximum number of tables to collect column statistics for.
          value:
            type: number
            example: 500
            display_default: 500
          fleet_configurable: false
        - name: include_databases
          description: |
            A list of regex patterns to include databases.
            Any database whose name matches any one of these patterns will be included.
            If empty, all databases matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "mydb"
          fleet_configurable: false
        - name: exclude_databases
          description: |
            A list of regex patterns to exclude databases.
            Any database whose name matches any one of these patterns will be excluded.
            If empty, all databases matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "privatedb.*"
          fleet_configurable: false
        - name: include_schemas
          description: |
            A list of regex patterns to include schemas.
            Any schema whose name matches any one of these patterns will be included.
            If empty, all schemas matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "myschema"
          fleet_configurable: false
        - name: exclude_schemas
          description: |
            A list of regex patterns to exclude schemas.
            Any schema whose name matches any one of these patterns will be excluded.
            If empty, all schemas matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "privateschema.*"
          fleet_configurable: false
        - name: include_tables
          description: |
            A list of regex patterns to include tables.
            Any table whose name matches any one of these patterns will be included.
            If empty, all tables matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "users.*"
          fleet_configurable: false
        - name: exclude_tables
          description: |
            A list of regex patterns to exclude tables.
            Any table whose name matches any one of these patterns will be excluded.
            If empty, all tables matching other filters are included.
          value:
            type: array
            items:
              type: string
            example:
              - "temp_.*"
          fleet_configurable: false
    - name: aws
      display_priority: 0
      description: |
        This block defines the configuration for AWS RDS and Aurora instances.

        Complete this section if you have installed the Datadog AWS Integration
        (https://docs.datadoghq.com/integrations/amazon_web_services) to enrich instances
        with Postgres integration telemetry.

        These values are only applied when `dbm: true` option is set.
      options:
        - name: instance_endpoint
          description: |
            Set to the Endpoint.Address of the instance the agent is connecting to.
            Use this value to allow association of RDS metrics with the instance when 
            connecting to the instance through a proxy or CNAME, or if you set `reported_hostname`
            to a different value from the instance endpoint.

            For more information on instance endpoints,
            see the AWS docs https://docs.aws.amazon.com/AmazonRDS/latest/APIReference/API_Endpoint.html
          value:
            type: string
            example: mydb.cfxgae8cilcf.us-east-1.rds.amazonaws.com
          fleet_configurable: false
        - name: region
          description: |
            Equal to the region of the instance the agent is connecting to.
            This value is used to configure IAM authentication.
          value:
            type: string
            example: us-east-1
          fleet_configurable: false
        - name: managed_authentication
          description: |
            Configure section used for AWS IAM Authentication with RDS.

            This supports using IAM database authentication to connect to your database instance.

            For more information on configuration, see
            https://docs.datadoghq.com/database_monitoring/guide/managed_authentication

            For more information on RDS IAM Authentication, see the AWS docs
            https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/UsingWithRDS.IAMDBAuth.Connecting.html

            To enable IAM Authentication, set `aws.managed_authentication.enabled` to `true`.
            If `aws.managed_authentication.enabled` is set, then the `password` fields will be ignored.
            `aws.region` is required to enable IAM Authentication.

            Optionally, you can set `aws.managed_authentication.role_arn` to specify the IAM role ARN.
            This can be used to perform cross-account authentication.
          value:
            type: object
            properties:
            - name: enabled
              type: boolean
              example: false
            - name: role_arn
              type: string
              example: arn:aws:iam::123456789012:role/MyRole
          fleet_configurable: false

    - name: gcp
      display_priority: 0
      description: |
        This block defines the configuration for Google Cloud SQL instances.

        Complete this section if you have installed the Datadog GCP Integration
        (https://docs.datadoghq.com/integrations/google_cloud_platform) to enrich instances
        with Postgres integration telemetry.

        These values are only applied when `dbm: true` option is set.
      options:
        - name: project_id
          description: |
            Equal to the GCP resource's project ID.

            For more information on project IDs,
            See the GCP docs https://cloud.google.com/resource-manager/docs/creating-managing-projects
          value:
            type: string
            example: foo-project
          fleet_configurable: false
        - name: instance_id
          description: |
            Equal to the GCP resource's instance ID.

            For more information on instance IDs,
            See the GCP docs https://cloud.google.com/sql/docs/postgres/instance-settings#instance-id-2ndgen
          value:
            type: string
            example: foo-database
          fleet_configurable: false

    - name: azure
      display_priority: 0
      description: |
        This block defines the configuration for Azure Database for PostgreSQL.

        Complete this section if you have installed the Datadog Azure Integration
        (https://docs.datadoghq.com/integrations/azure) to enrich instances
        with Postgres integration telemetry.
        These values are only applied when `dbm: true` option is set.
      options:
        - name: deployment_type
          description: |
            Equal to the deployment type for the managed database.

            Acceptable values are:
              - `flexible_server`
              - `single_server`
              - `virtual_machine`

            For more information on deployment types,
            see the Azure docs https://docs.microsoft.com/en-us/azure/postgresql/overview-postgres-choose-server-options
          value:
            type: string
            example: flexible_server
          fleet_configurable: false
        - name: fully_qualified_domain_name
          description: |
            Equal to the full qualified domain name of the Azure PostgreSQL database.

            This value is optional if the value of `host` is already configured to the fully qualified domain name.
          value:
            type: string
            example: my-postgres-database.database.windows.net
          fleet_configurable: false
        - name: managed_authentication
          description: |
            Configuration section used for Azure AD Authentication.

            This supports using System or User assigned managed identities, as well as
            workload identity federation (e.g. on AKS).

            If enabled, the `password` field will be ignored.

            For more information on configuration, see
            https://docs.datadoghq.com/database_monitoring/guide/managed_authentication

            For more information on Managed Identities, see the Azure docs
            https://learn.microsoft.com/en-us/azure/active-directory/managed-identities-azure-resources/overview

            For more information on Workload Identity, see the Azure docs
            https://learn.microsoft.com/en-us/azure/aks/workload-identity-overview

            The following fields are supported:

            enabled: Set to `true` to enable Azure AD authentication.
            auth_type: The authentication method. Use `managed_identity` (default) or `workload_identity` for AKS.
            client_id: The client ID of the managed identity or app registration. Required for `managed_identity`.
              Optional for `workload_identity` (defaults to the `AZURE_CLIENT_ID` environment variable).
            tenant_id: The Azure AD tenant ID. Only used for `workload_identity`
              (defaults to the `AZURE_TENANT_ID` environment variable).
            identity_scope: The permission scope for the identity token.
          value:
            type: object
            properties:
            - name: enabled
              type: boolean
              example: false
            - name: auth_type
              type: string
              example: managed_identity
              description: |
                The authentication method. Use `managed_identity` (default) or `workload_identity` for AKS.
            - name: client_id
              description: |
                The client ID of the managed identity or application registration.
                Required for `managed_identity` auth. Optional for `workload_identity`,
                where it defaults to the `AZURE_CLIENT_ID` environment variable.
              type: string
            - name: tenant_id
              description: |
                The Azure AD tenant ID. Only used for `workload_identity` auth.
                Defaults to the `AZURE_TENANT_ID` environment variable.
              type: string
            - name: identity_scope
              description: |
                The permission scope from where to access the identity token.
              type: string
              example: https://ossrdbms-aad.database.windows.net/.default
          fleet_configurable: false
    - name: obfuscator_options
      display_priority: 0
      description: |
        Configure how the SQL obfuscator behaves.
        Note: This option only applies when `dbm` is enabled.
      options:
        - name: obfuscation_mode
          description: |
            Set the obfuscation mode. The obfuscation mode determines how the SQL obfuscator will obfuscate your SQL
            statements. The following modes are supported:
            - `obfuscate_only`: Obfuscate the SQL statement without normalizing the statement.
            - `obfuscate_and_normalize`: Obfuscate the SQL statement and normalize the statement.
          value:
            type: string
            example: obfuscate_and_normalize
            display_default: obfuscate_and_normalize
          fleet_configurable: false
        - name: replace_digits
          description: |
            Set to `true` to replace digits in identifiers and table names with question marks in your SQL statements.
            Note: This option also applies to extracted tables using `collect_tables`.
          value:
            type: boolean
            example: false
          fleet_configurable: false
        - name: collect_metadata
          description: |
            Set to `false` to disable the collection of metadata in your SQL statements.
            Metadata includes things such as tables, commands, and comments.
          value:
            type: boolean
            example: true
          fleet_configurable: false
        - name: collect_tables
          fleet_configurable: true
          description: |
            Set to `false` to disable the collection of tables in your SQL statements.
            Requires `collect_metadata: true`.
          value:
            type: boolean
            example: true
        - name: collect_commands
          fleet_configurable: true
          description: |
            Set to `false` to disable the collection of commands in your SQL statements.
            Requires `collect_metadata: true`.

            Examples: SELECT, UPDATE, DELETE, etc.
          value:
            type: boolean
            example: true
        - name: collect_comments
          fleet_configurable: true
          description: |
            Set to `false` to disable the collection of comments in your SQL statements.
            Requires `collect_metadata: true`.
            Note: This option must be `true` in order to correlate Database Monitoring samples and APM traces.
            See https://docs.datadoghq.com/database_monitoring/connect_dbm_and_apm
          value:
            type: boolean
            example: true
        - name: keep_sql_alias
          fleet_configurable: true
          description: |
            Set to `true` to keep SQL aliases in obfuscated SQL statements. Examples of aliases are
            `with select 1 as alias`, `select column as other_name`, or `select * from table t`.
            When `true` these aliases will not be removed.
          value:
            type: boolean
            example: true
            display_default: true
        - name: keep_dollar_quoted_func
          fleet_configurable: true
          description: |
            Set to `true` to prevent dollar quoted function strings (e.g. `$func$`) from being removed.
            When not removed, the sql content of dollar quoted func strings will be obfuscated.
            Only strings with the tag `$func$` are supported.
          value:
            type: boolean
            example: true
            display_default: true
        - name: remove_space_between_parentheses
          fleet_configurable: true
          description: |
            Set to `true` to remove spaces between parentheses in your normalized SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
        - name: keep_null
          fleet_configurable: true
          description: |
            Set to `true` to keep the keyword `NULL` in your obfuscated SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
        - name: keep_boolean
          fleet_configurable: true
          description: |
            Set to `true` to keep the keywords `TRUE` and `FALSE` in your obfuscated SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
        - name: keep_positional_parameter
          fleet_configurable: true
          description: |
            Set to `true` to keep positional parameters (e.g. `$1`) in your obfuscated SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
        - name: keep_trailing_semicolon
          fleet_configurable: true
          description: |
            Set to `true` to keep trailing semicolons in your normalized SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
        - name: keep_identifier_quotation
          fleet_configurable: true
          description: |
            Set to `true` to keep identifier quotations (e.g. `"my_table"`) in your normalized SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
        - name: keep_json_path
          fleet_configurable: true
          description: |
            Set to `true` to keep JSON path expressions (e.g. `data->'key'`) in your normalized SQL statements.
          value:
            type: boolean
            example: false
            display_default: false
    - name: collect_raw_query_statement
      display_priority: 0
      fleet_configurable: true
      description: |
        Configure the collection of raw query statements in query samples and explain plans.
        Raw query statements and explain plans may contain sensitive information (e.g., passwords)
        or personally identifiable information in query text.
        Enabling this option will allow the collection and ingestion of raw query statements and 
        explain plans into Datadog, which can then become viewable in query samples or explain plans. 
        This option is disabled by default.
        Note: Collection of raw query statements is currently in preview.
        This option only applies when dbm is enabled.
      options:
        - name: enabled
          fleet_configurable: true
          description: |
            Set to `true` to collect the raw query statements.
          value:
            type: boolean
            example: false
            display_default: false
    - name: log_unobfuscated_queries
      display_priority: 0
      fleet_configurable: true
      hidden: true
      description: |
        Set to `true` to enable logging of original unobfuscated SQL queries when obfuscation errors occur.
        For security purposes, it is recommended to use this option for debugging only when requested by Datadog Support.
        Note: This option only applies when `dbm` is enabled.
      value:
        type: boolean
        example: false
        display_default: false
    - name: log_unobfuscated_plans
      display_priority: 0
      hidden: true
      description: |
        Set to `true` to enable logging of original unobfuscated SQL plans when obfuscation errors occur.
        For security purposes, it is recommended to use this option for debugging only when requested by Datadog Support.
        Note: This option only applies when `dbm` is enabled.
      value:
        type: boolean
        example: false
        display_default: false
      fleet_configurable: false
    - name: database_instance_collection_interval
      display_priority: 0
      hidden: true
      fleet_configurable: true
      description: |
        Set the database instance collection interval (in seconds). The database instance collection sends
        basic information about the database instance along with a signal that it still exists.
        This collection does not involve any additional queries to the database.
      value:
        type: number
        default: 300
    - name: propagate_agent_tags
      display_priority: 0
      fleet_configurable: true
      description: |
        Set to `true` to propagate the tags from `datadog.yaml` and the agent host tags to the check.

        When set to `true`, the tags from the agent host are added to the check's tags for all instances.
        This option takes precedence over the `propagate_agent_tags` option in `init_config`.
      value:
        example: false
        type: boolean
    - name: automatic_diagnostics
      fleet_configurable: false
      hidden: true
      description: |
        Configure automatic diagnostics. When enabled, the integration runs its setup diagnostics and
        reports the results to the Datadog platform.
      options:
        - name: enabled
          description: Set to `true` to enable automatic diagnostics.
          value:
            type: boolean
            example: false
            display_default: false
          hidden: true
          fleet_configurable: false
        - name: interval
          description: |
            Set the interval (in seconds) at which automatic diagnostics run. The diagnostics run at
            most once per interval.
          value:
            type: number
            example: 600
            display_default: 600
          hidden: true
          fleet_configurable: false
    - template: instances/db
      overrides:
        custom_queries.value.example:
          - query: "SELECT foo, COUNT(*) FROM table.events GROUP BY foo"
            columns:
              - name: foo
                type: tag
              - name: event.total
                type: gauge
            tags:
              - test:postgresql
            metric_prefix: postgresql
        custom_queries.display_priority: 0
    - template: instances/default
      overrides:
        disable_generic_tags.hidden: False
        disable_generic_tags.enabled: True
        disable_generic_tags.description: The integration will stop sending server tag as is reduntant with host tag
        tags.display_priority: 0
        min_collection_interval.display_priority: 0
        disable_generic_tags.display_priority: 0
        empty_default_hostname.display_priority: 0
  - template: logs
    example:
    - type: file
      path:  /path/to/postgres.log
      source: postgresql
      service: <SERVICE>
      log_processing_rules:
        - type: multi_line
          pattern: \d{4}\-(0?[1-9]|1[012])\-(0?[1-9]|[12][0-9]|3[01])
          name: new_log_start_with_date