database.yaml

groups:
  - id: db
    prefix: db
    type: span
    brief: >
      This document defines the attributes used to perform database client calls.
    span_kind: client
    attributes:
      - id: system
        tag: connection-level
        brief: An identifier for the database management system (DBMS) product being used. See below for a list of well-known identifiers.
        requirement_level: required
        type:
          allow_custom_values: true
          members:
            - id: other_sql
              value: 'other_sql'
              brief: 'Some other SQL database. Fallback only. See notes.'
            - id: mssql
              value: 'mssql'
              brief: 'Microsoft SQL Server'
            - id: mssqlcompact
              value: 'mssqlcompact'
              brief: 'Microsoft SQL Server Compact'
            - id: mysql
              value: 'mysql'
              brief: 'MySQL'
            - id: oracle
              value: 'oracle'
              brief: 'Oracle Database'
            - id: db2
              value: 'db2'
              brief: 'IBM Db2'
            - id: postgresql
              value: 'postgresql'
              brief: 'PostgreSQL'
            - id: redshift
              value: 'redshift'
              brief: 'Amazon Redshift'
            - id: hive
              value: 'hive'
              brief: 'Apache Hive'
            - id: cloudscape
              value: 'cloudscape'
              brief: 'Cloudscape'
            - id: hsqldb
              value: 'hsqldb'
              brief: 'HyperSQL DataBase'
            - id: progress
              value: 'progress'
              brief: 'Progress Database'
            - id: maxdb
              value: 'maxdb'
              brief: 'SAP MaxDB'
            - id: hanadb
              value: 'hanadb'
              brief: 'SAP HANA'
            - id: ingres
              value: 'ingres'
              brief: 'Ingres'
            - id: firstsql
              value: 'firstsql'
              brief: 'FirstSQL'
            - id: edb
              value: 'edb'
              brief: 'EnterpriseDB'
            - id: cache
              value: 'cache'
              brief: 'InterSystems Caché'
            - id: adabas
              value: 'adabas'
              brief: 'Adabas (Adaptable Database System)'
            - id: firebird
              value: 'firebird'
              brief: 'Firebird'
            - id: derby
              value: 'derby'
              brief: 'Apache Derby'
            - id: filemaker
              value: 'filemaker'
              brief: 'FileMaker'
            - id: informix
              value: 'informix'
              brief: 'Informix'
            - id: instantdb
              value: 'instantdb'
              brief: 'InstantDB'
            - id: interbase
              value: 'interbase'
              brief: 'InterBase'
            - id: mariadb
              value: 'mariadb'
              brief: 'MariaDB'
            - id: netezza
              value: 'netezza'
              brief: 'Netezza'
            - id: pervasive
              value: 'pervasive'
              brief: 'Pervasive PSQL'
            - id: pointbase
              value: 'pointbase'
              brief: 'PointBase'
            - id: sqlite
              value: 'sqlite'
              brief: 'SQLite'
            - id: sybase
              value: 'sybase'
              brief: 'Sybase'
            - id: teradata
              value: 'teradata'
              brief: 'Teradata'
            - id: vertica
              value: 'vertica'
              brief: 'Vertica'
            - id: h2
              value: 'h2'
              brief: 'H2'
            - id: coldfusion
              value: 'coldfusion'
              brief: 'ColdFusion IMQ'
            - id: cassandra
              value: 'cassandra'
              brief: 'Apache Cassandra'
            - id: hbase
              value: 'hbase'
              brief: 'Apache HBase'
            - id: mongodb
              value: 'mongodb'
              brief: 'MongoDB'
            - id: redis
              value: 'redis'
              brief: 'Redis'
            - id: couchbase
              value: 'couchbase'
              brief: 'Couchbase'
            - id: couchdb
              value: 'couchdb'
              brief: 'CouchDB'
            - id: cosmosdb
              value: 'cosmosdb'
              brief: 'Microsoft Azure Cosmos DB'
            - id: dynamodb
              value: 'dynamodb'
              brief: 'Amazon DynamoDB'
            - id: neo4j
              value: 'neo4j'
              brief: 'Neo4j'
            - id: geode
              value: 'geode'
              brief: 'Apache Geode'
            - id: elasticsearch
              value: 'elasticsearch'
              brief: 'Elasticsearch'
            - id: memcached
              value: 'memcached'
              brief: 'Memcached'
            - id: cockroachdb
              value: 'cockroachdb'
              brief: 'CockroachDB'
            - id: opensearch
              value: 'opensearch'
              brief: 'OpenSearch'
            - id: clickhouse
              value: 'clickhouse'
              brief: 'ClickHouse'
            - id: spanner
              value: 'spanner'
              brief: 'Cloud Spanner'
            - id: trino
              value: 'trino'
              brief: 'Trino'
      - id: connection_string
        tag: connection-level
        type: string
        brief: >
          The connection string used to connect to the database.
          It is recommended to remove embedded credentials.
        examples: 'Server=(localdb)\v11.0;Integrated Security=true;'
      - id: user
        tag: connection-level
        type: string
        brief: >
          Username for accessing the database.
        examples: ['readonly_user', 'reporting_user']
      - id: jdbc.driver_classname
        tag: connection-level-tech-specific
        type: string
        brief: >
          The fully-qualified class name of the [Java Database Connectivity (JDBC)](https://docs.oracle.com/javase/8/docs/technotes/guides/jdbc/) driver used to connect.
        examples: ['org.postgresql.Driver', 'com.microsoft.sqlserver.jdbc.SQLServerDriver']
      - id: name
        tag: call-level
        type: string
        requirement_level:
          conditionally_required: If applicable.
        brief: >
          This attribute is used to report the name of the database being accessed.
          For commands that switch the database, this should be set to the target database
          (even if the command fails).
        note: >
          In some SQL databases, the database name to be used is called "schema name".
          In case there are multiple layers that could be considered for database name
          (e.g. Oracle instance name and schema name),
          the database name to be used is the more specific layer (e.g. Oracle schema name).
        examples: [ 'customers', 'main' ]
      - id: statement
        tag: call-level
        type: string
        requirement_level:
          recommended: >
            Should be collected by default only if there is sanitization that excludes sensitive information.
        brief: >
          The database statement being executed.
        examples: ['SELECT * FROM wuser_table', 'SET mykey "WuValue"']
      - id: operation
        tag: call-level
        type: string
        requirement_level:
          conditionally_required: If `db.statement` is not applicable.
        brief: >
          The name of the operation being executed, e.g. the [MongoDB command name](https://docs.mongodb.com/manual/reference/command/#database-operations)
          such as `findAndModify`, or the SQL keyword.
        note: >
          When setting this to an SQL keyword, it is not recommended to
          attempt any client-side parsing of `db.statement` just to get this
          property, but it should be set if the operation name is provided by
          the library being instrumented.
          If the SQL statement has an ambiguous operation, or performs more
          than one operation, this value may be omitted.
        examples: ['findAndModify', 'HMSET', 'SELECT']
      - ref: server.address
        tag: connection-level
        brief: >
          Name of the database host.
      - ref: server.port
        tag: connection-level
        requirement_level:
          conditionally_required: If using a port other than the default port for this DBMS and if `server.address` is set.
      - ref: network.peer.address
        requirement_level:
          recommended: If different than `server.address`.
        tag: connection-level
      - ref: network.peer.port
        requirement_level:
          recommended: If `network.peer.address` is set.
        tag: connection-level
      - ref: network.transport
        tag: connection-level
      - ref: network.type
        tag: connection-level

  - id: db.mssql
    prefix: db.mssql
    type: span
    extends: db
    brief: >
      Connection-level attributes for Microsoft SQL Server
    attributes:
      - id: instance_name
        tag: connection-level-tech-specific
        type: string
        note: >
          If setting a `db.mssql.instance_name`, `server.port` is no longer
          required (but still recommended if non-standard).
        brief: >
          The Microsoft SQL Server [instance name](https://docs.microsoft.com/sql/connect/jdbc/building-the-connection-url?view=sql-server-ver15)
          connecting to. This name is used to determine the port of a named instance.
        examples: 'MSSQLSERVER'

  - id: db.cassandra
    prefix: db.cassandra
    type: span
    extends: db
    brief: >
      Call-level attributes for Cassandra
    attributes:
      - ref: db.name
        tag: call-level-tech-specific-cassandra
        brief: >
          The keyspace name in Cassandra.
        examples: ["mykeyspace"]
        note: For Cassandra the `db.name` should be set to the Cassandra keyspace name.
      - id: page_size
        type: int
        tag: call-level-tech-specific-cassandra
        brief: >
          The fetch size used for paging, i.e. how many rows will be returned at once.
        examples: [5000]
      - id: consistency_level
        tag: call-level-tech-specific-cassandra
        brief: >
          The consistency level of the query. Based on consistency values from [CQL](https://docs.datastax.com/en/cassandra-oss/3.0/cassandra/dml/dmlConfigConsistency.html).
        type:
          members:
            - id: all
              value: 'all'
            - id: each_quorum
              value: 'each_quorum'
            - id: quorum
              value: 'quorum'
            - id: local_quorum
              value: 'local_quorum'
            - id: one
              value: 'one'
            - id: two
              value: 'two'
            - id: three
              value: 'three'
            - id: local_one
              value: 'local_one'
            - id: any
              value: 'any'
            - id: serial
              value: 'serial'
            - id: local_serial
              value: 'local_serial'
      - id: table
        type: string
        tag: call-level-tech-specific-cassandra
        requirement_level: recommended
        brief: The name of the primary table that the operation is acting upon, including the keyspace name (if applicable).
        note: >
          This mirrors the db.sql.table attribute but references cassandra rather than sql.
          It is not recommended to attempt any client-side parsing of
          `db.statement` just to get this property, but it should be set if
          it is provided by the library being instrumented.
          If the operation is acting upon an anonymous table, or more than one table, this
          value MUST NOT be set.
        examples: 'mytable'
      - id: idempotence
        type: boolean
        tag: call-level-tech-specific-cassandra
        brief: >
          Whether or not the query is idempotent.
      - id: speculative_execution_count
        type: int
        tag: call-level-tech-specific-cassandra
        brief: >
          The number of times a query was speculatively executed. Not set or `0` if the query was not executed speculatively.
        examples: [0, 2]
      - id: coordinator.id
        type: string
        tag: call-level-tech-specific-cassandra
        brief: >
          The ID of the coordinating node for a query.
        examples: 'be13faa2-8574-4d71-926d-27f16cf8a7af'
      - id: coordinator.dc
        type: string
        tag: call-level-tech-specific-cassandra
        brief: >
          The data center of the coordinating node for a query.
        examples: 'us-west-2'

  - id: db.hbase
    prefix: db.hbase
    type: span
    extends: db
    brief: >
      Call-level attributes for HBase
    attributes:
      - ref: db.name
        tag: call-level-tech-specific
        brief: >
          The HBase namespace.
        examples: ['mynamespace']
        note: For HBase the `db.name` should be set to the HBase namespace.

  - id: db.couchdb
    prefix: db.couchdb
    type: span
    extends: db
    brief: >
      Call-level attributes for CouchDB
    attributes:
      - ref: db.operation
        tag: call-level-tech-specific
        brief: >
          The HTTP method + the target REST route.
        examples: ['GET /{db}/{docid}']
        note: >
          In **CouchDB**, `db.operation` should be set to the HTTP method +
          the target REST route according to the API reference documentation.
          For example, when retrieving a document, `db.operation` would be set to
          (literally, i.e., without replacing the placeholders with concrete values):
          [`GET /{db}/{docid}`](http://docs.couchdb.org/en/stable/api/document/common.html#get--db-docid).

  - id: db.redis
    prefix: db.redis
    type: span
    extends: db
    brief: >
      Call-level attributes for Redis
    attributes:
      - id: database_index
        type: int
        requirement_level:
          conditionally_required: If other than the default database (`0`).
        tag: call-level-tech-specific
        brief: >
          The index of the database being accessed as used in the [`SELECT` command](https://redis.io/commands/select), provided as an integer.
          To be used instead of the generic `db.name` attribute.
        examples: [0, 1, 15]
      - ref: db.statement
        tag: call-level-tech-specific
        brief: >
          The full syntax of the Redis CLI command.
        examples: ["HMSET myhash field1 'Hello' field2 'World'"]
        note: >
          For **Redis**, the value provided for `db.statement` SHOULD correspond to the syntax of the Redis CLI.
          If, for example, the [`HMSET` command](https://redis.io/commands/hmset) is invoked, `"HMSET myhash field1 'Hello' field2 'World'"` would be a suitable value for `db.statement`.

  - id: db.mongodb
    prefix: db.mongodb
    type: span
    extends: db
    brief: >
      Call-level attributes for MongoDB
    attributes:
      - id: collection
        type: string
        requirement_level: required
        tag: call-level-tech-specific
        brief: >
          The collection being accessed within the database stated in `db.name`.
        examples: [ 'customers', 'products' ]

  - id: db.elasticsearch
    prefix: db.elasticsearch
    type: span
    extends: db
    brief: >
      Call-level attributes for Elasticsearch
    attributes:
      - ref: http.request.method
        requirement_level: required
      - ref: db.operation
        requirement_level: required
        brief: The endpoint identifier for the request.
        examples: [ 'search', 'ml.close_job', 'cat.aliases' ]
      - ref: url.full
        requirement_level: required
        examples: [ 'https://localhost:9200/index/_search?q=user.id:kimchy' ]
      - ref: db.statement
        requirement_level:
          recommended: >
            Should be collected by default for search-type queries and only if there is sanitization that excludes
            sensitive information.
        brief: The request body for a [search-type query](https://www.elastic.co/guide/en/elasticsearch/reference/current/search.html), as a json string.
        examples: [ '"{\"query\":{\"term\":{\"user.id\":\"kimchy\"}}}"' ]
      - ref: server.address
      - ref: server.port
      - id: cluster.name
        type: string
        requirement_level:
          recommended: >
            When communicating with an Elastic Cloud deployment, this should be collected from the "X-Found-Handling-Cluster" HTTP response header.
        tag: call-level-tech-specific
        brief: >
          Represents the identifier of an Elasticsearch cluster.
        examples: ["e9106fc68e3044f0b1475b04bf4ffd5f"]
      - id: node.name
        type: string
        requirement_level:
          recommended: >
            When communicating with an Elastic Cloud deployment, this should be collected from the "X-Found-Handling-Instance" HTTP response header.
        tag: call-level-tech-specific
        brief: >
          Represents the human-readable identifier of the node/instance to which a request was routed.
        examples: ["instance-0000000001"]
      - id: path_parts
        type: template[string]
        requirement_level:
          conditionally_required: when the url has dynamic values
        tag: call-level-tech-specific
        brief: >
          A dynamic value in the url path.
        note: >
          Many Elasticsearch url paths allow dynamic values. These SHOULD be recorded in span attributes in the format
          `db.elasticsearch.path_parts.<key>`, where `<key>` is the url path part name. The implementation SHOULD
          reference the [elasticsearch schema](https://raw.githubusercontent.com/elastic/elasticsearch-specification/main/output/schema/schema.json)
          in order to map the path part values to their names.
        examples: ['db.elasticsearch.path_parts.index=test-index', 'db.elasticsearch.path_parts.doc_id=123']

  - id: db.sql
    prefix: 'db.sql'
    type: span
    extends: 'db'
    brief: >
      Call-level attributes for SQL databases
    attributes:
      - id: table
        tag: call-level-tech-specific
        type: string
        requirement_level: recommended
        brief: The name of the primary table that the operation is acting upon, including the database name (if applicable).
        note: >
          It is not recommended to attempt any client-side parsing of
          `db.statement` just to get this property, but it should be set if
          it is provided by the library being instrumented.
          If the operation is acting upon an anonymous table, or more than one table, this
          value MUST NOT be set.
        examples: ['public.users', 'customers']

  - id: db.cosmosdb
    type: span
    extends: db
    prefix: db.cosmosdb
    brief: >
      Call-level attributes for Cosmos DB.
    attributes:
      - id: client_id
        type: string
        brief: Unique Cosmos client instance id.
        examples: '3ba4827d-4422-483f-b59f-85b74211c11d'
      - id: operation_type
        type:
          allow_custom_values: true
          members:
            - id: invalid
              value: 'Invalid'
            - id: create
              value: 'Create'
            - id: patch
              value: 'Patch'
            - id: read
              value: 'Read'
            - id: read_feed
              value: 'ReadFeed'
            - id: delete
              value: 'Delete'
            - id: replace
              value: 'Replace'
            - id: execute
              value: 'Execute'
            - id: query
              value: 'Query'
            - id: head
              value: 'Head'
            - id: head_feed
              value: 'HeadFeed'
            - id: upsert
              value: 'Upsert'
            - id: batch
              value: 'Batch'
            - id: query_plan
              value: 'QueryPlan'
            - id: execute_javascript
              value: 'ExecuteJavaScript'
        brief: CosmosDB Operation Type.
        requirement_level:
          conditionally_required: when performing one of the operations in this list
      - ref: user_agent.original
        brief: 'Full user-agent string is generated by Cosmos DB SDK'
        note: >
          The user-agent value is generated by SDK which is a combination of<br>
          `sdk_version` : Current version of SDK. e.g. 'cosmos-netstandard-sdk/3.23.0'<br>
          `direct_pkg_version` : Direct package version used by Cosmos DB SDK. e.g. '3.23.1'<br>
          `number_of_client_instances` : Number of cosmos client instances created by the application. e.g. '1'<br>
          `type_of_machine_architecture` : Machine architecture. e.g. 'X64'<br>
          `operating_system` : Operating System. e.g. 'Linux 5.4.0-1098-azure 104 18'<br>
          `runtime_framework` : Runtime Framework. e.g. '.NET Core 3.1.32'<br>
          `failover_information` : Generated key to determine if region failover enabled.
             Format Reg-{D (Disabled discovery)}-S(application region)|L(List of preferred regions)|N(None, user did not configure it).
             Default value is "NS".
        examples: ['cosmos-netstandard-sdk/3.23.0\|3.23.1\|1\|X64\|Linux 5.4.0-1098-azure 104 18\|.NET Core 3.1.32\|S\|']
      - id: connection_mode
        type:
          allow_custom_values: false
          members:
            - id: gateway
              value: 'gateway'
              brief: Gateway (HTTP) connections mode
            - id: direct
              value: 'direct'
              brief: Direct connection.
        brief: Cosmos client connection mode.
        requirement_level:
          conditionally_required: if not `direct` (or pick gw as default)
      - id: container
        type: string
        brief: Cosmos DB container name.
        requirement_level:
          conditionally_required: if available
        examples: 'anystring'
      - id: request_content_length
        type: int
        brief: Request payload size in bytes
      - id: status_code
        type: int
        brief: Cosmos DB status code.
        examples: [200, 201]
        requirement_level:
          conditionally_required: if response was received
      - id: sub_status_code
        type: int
        brief: Cosmos DB sub status code.
        examples: [1000, 1002]
        requirement_level:
          conditionally_required: when response was received and contained sub-code.
      - id: request_charge
        type: double
        brief: RU consumed for that operation
        examples: [46.18, 1.0]
        requirement_level:
          conditionally_required: when available

  - id: db.tech
    type: span
    brief: "Semantic convention group for specific technologies"
    constraints:
      - include: 'db.cassandra'
      - include: 'db.redis'
      - include: 'db.mongodb'
      - include: 'db.sql'
      - include: 'db.cosmosdb'