Skip to content

[AWS Usage] Overlapping documents when enabling TSDB - no more dimensions available #6783

@constanca-m

Description

@constanca-m

Currently there is no way to distinguish between some documents from AWS Usage. If we enable TSDB with the dimensions set as of now, they will not be enough and we will end up losing data. However, there are no keyword fields available to differentiate between the these set of documents. Example:

Document 1
{
  "_index": ".ds-metrics-aws.usage-default-2023.06.29-000001",
  "_id": "VaIZB4kBLpMqNjezszQ9",
  "_version": 1,
  "_score": 0,
  "_source": {
    "cloud": {
      "provider": "aws",
      "region": "sa-east-1",
      "account": {
        "name": "elastic-observability",
        "id": "627286350134"
      }
    },
    "agent": {
      "name": "kind-control-plane",
      "id": "178edbcb-2132-497d-b6da-e8c7d8095a90",
      "type": "metricbeat",
      "ephemeral_id": "e63bc826-7b49-4d1d-85f0-40340b77461d",
      "version": "8.8.0"
    },
    "@timestamp": "2023-06-29T12:20:00.000Z",
    "ecs": {
      "version": "8.0.0"
    },
    "data_stream": {
      "namespace": "default",
      "type": "metrics",
      "dataset": "aws.usage"
    },
    "service": {
      "type": "aws"
    },
    "elastic_agent": {
      "id": "178edbcb-2132-497d-b6da-e8c7d8095a90",
      "version": "8.8.0",
      "snapshot": true
    },
    "host": {
      "hostname": "kind-control-plane",
      "os": {
        "kernel": "5.15.49-linuxkit",
        "codename": "focal",
        "name": "Ubuntu",
        "type": "linux",
        "family": "debian",
        "version": "20.04.6 LTS (Focal Fossa)",
        "platform": "ubuntu"
      },
      "containerized": false,
      "ip": [
        "10.244.0.1",
        "10.244.0.1",
        "10.244.0.1",
        "172.18.0.2",
        "fc00:f853:ccd:e793::2",
        "fe80::42:acff:fe12:2",
        "172.19.0.4"
      ],
      "name": "kind-control-plane",
      "id": "0aab3a64904042bdb1c956d6fe2fa4f1",
      "mac": [
        "02-42-AC-12-00-02",
        "02-42-AC-13-00-04",
        "06-DD-17-EE-41-97",
        "22-F1-EB-33-1A-13",
        "66-56-4C-AB-83-C0"
      ],
      "architecture": "x86_64"
    },
    "metricset": {
      "period": 60000,
      "name": "cloudwatch"
    },
    "aws": {
      "usage": {
        "metrics": {
          "CallCount": {
            "sum": 28
          }
        }
      },
      "cloudwatch": {
        "namespace": "AWS/Usage"
      },
      "dimensions": {
        "Type": "API",
        "Resource": "ListMetrics",
        "Service": "CloudWatch",
        "Class": "None"
      }
    },
    "event": {
      "duration": 9649888084,
      "agent_id_status": "verified",
      "ingested": "2023-06-29T12:21:12Z",
      "module": "aws",
      "dataset": "aws.usage"
    }
  },
  "fields": {
    "elastic_agent.version": [
      "8.8.0"
    ],
    "host.os.name.text": [
      "Ubuntu"
    ],
    "host.hostname": [
      "kind-control-plane"
    ],
    "host.mac": [
      "02-42-AC-12-00-02",
      "02-42-AC-13-00-04",
      "06-DD-17-EE-41-97",
      "22-F1-EB-33-1A-13",
      "66-56-4C-AB-83-C0"
    ],
    "service.type": [
      "aws"
    ],
    "host.ip": [
      "10.244.0.1",
      "10.244.0.1",
      "10.244.0.1",
      "172.18.0.2",
      "fc00:f853:ccd:e793::2",
      "fe80::42:acff:fe12:2",
      "172.19.0.4"
    ],
    "agent.type": [
      "metricbeat"
    ],
    "aws.dimensions.Class": [
      "None"
    ],
    "event.module": [
      "aws"
    ],
    "host.os.version": [
      "20.04.6 LTS (Focal Fossa)"
    ],
    "host.os.kernel": [
      "5.15.49-linuxkit"
    ],
    "host.os.name": [
      "Ubuntu"
    ],
    "aws.cloudwatch.namespace": [
      "AWS/Usage"
    ],
    "agent.name": [
      "kind-control-plane"
    ],
    "elastic_agent.snapshot": [
      true
    ],
    "host.name": [
      "kind-control-plane"
    ],
    "event.agent_id_status": [
      "verified"
    ],
    "aws.dimensions.Service": [
      "CloudWatch"
    ],
    "host.id": [
      "0aab3a64904042bdb1c956d6fe2fa4f1"
    ],
    "aws.usage.metrics.CallCount.sum": [
      28
    ],
    "cloud.region": [
      "sa-east-1"
    ],
    "host.os.type": [
      "linux"
    ],
    "cloud.account.name": [
      "elastic-observability"
    ],
    "elastic_agent.id": [
      "178edbcb-2132-497d-b6da-e8c7d8095a90"
    ],
    "data_stream.namespace": [
      "default"
    ],
    "metricset.period": [
      60000
    ],
    "aws.dimensions.Type": [
      "API"
    ],
    "host.os.codename": [
      "focal"
    ],
    "data_stream.type": [
      "metrics"
    ],
    "event.duration": [
      9649888084
    ],
    "host.architecture": [
      "x86_64"
    ],
    "metricset.name": [
      "cloudwatch"
    ],
    "cloud.provider": [
      "aws"
    ],
    "event.ingested": [
      "2023-06-29T12:21:12.000Z"
    ],
    "@timestamp": [
      "2023-06-29T12:20:00.000Z"
    ],
    "agent.id": [
      "178edbcb-2132-497d-b6da-e8c7d8095a90"
    ],
    "host.containerized": [
      false
    ],
    "ecs.version": [
      "8.0.0"
    ],
    "host.os.platform": [
      "ubuntu"
    ],
    "cloud.account.id": [
      "627286350134"
    ],
    "data_stream.dataset": [
      "aws.usage"
    ],
    "agent.ephemeral_id": [
      "e63bc826-7b49-4d1d-85f0-40340b77461d"
    ],
    "agent.version": [
      "8.8.0"
    ],
    "aws.dimensions.Resource": [
      "ListMetrics"
    ],
    "host.os.family": [
      "debian"
    ],
    "event.dataset": [
      "aws.usage"
    ]
  }
}
Document 2
{
  "_index": ".ds-metrics-aws.usage-default-2023.06.29-000001",
  "_id": "aaIaB4kBLpMqNjezKDWL",
  "_version": 1,
  "_score": 0,
  "_source": {
    "cloud": {
      "provider": "aws",
      "region": "sa-east-1",
      "account": {
        "name": "elastic-observability",
        "id": "627286350134"
      }
    },
    "agent": {
      "name": "kind-control-plane",
      "id": "178edbcb-2132-497d-b6da-e8c7d8095a90",
      "type": "metricbeat",
      "ephemeral_id": "e63bc826-7b49-4d1d-85f0-40340b77461d",
      "version": "8.8.0"
    },
    "@timestamp": "2023-06-29T12:20:00.000Z",
    "ecs": {
      "version": "8.0.0"
    },
    "service": {
      "type": "aws"
    },
    "data_stream": {
      "namespace": "default",
      "type": "metrics",
      "dataset": "aws.usage"
    },
    "host": {
      "hostname": "kind-control-plane",
      "os": {
        "kernel": "5.15.49-linuxkit",
        "codename": "focal",
        "name": "Ubuntu",
        "type": "linux",
        "family": "debian",
        "version": "20.04.6 LTS (Focal Fossa)",
        "platform": "ubuntu"
      },
      "ip": [
        "10.244.0.1",
        "10.244.0.1",
        "10.244.0.1",
        "172.18.0.2",
        "fc00:f853:ccd:e793::2",
        "fe80::42:acff:fe12:2",
        "172.19.0.4"
      ],
      "containerized": false,
      "name": "kind-control-plane",
      "id": "0aab3a64904042bdb1c956d6fe2fa4f1",
      "mac": [
        "02-42-AC-12-00-02",
        "02-42-AC-13-00-04",
        "06-DD-17-EE-41-97",
        "22-F1-EB-33-1A-13",
        "66-56-4C-AB-83-C0"
      ],
      "architecture": "x86_64"
    },
    "elastic_agent": {
      "id": "178edbcb-2132-497d-b6da-e8c7d8095a90",
      "version": "8.8.0",
      "snapshot": true
    },
    "metricset": {
      "period": 60000,
      "name": "cloudwatch"
    },
    "aws": {
      "usage": {
        "metrics": {
          "CallCount": {
            "sum": 40
          }
        }
      },
      "cloudwatch": {
        "namespace": "AWS/Usage"
      },
      "dimensions": {
        "Type": "API",
        "Resource": "ListMetrics",
        "Service": "CloudWatch",
        "Class": "None"
      }
    },
    "event": {
      "duration": 9720431083,
      "agent_id_status": "verified",
      "ingested": "2023-06-29T12:21:42Z",
      "module": "aws",
      "dataset": "aws.usage"
    }
  },
  "fields": {
    "elastic_agent.version": [
      "8.8.0"
    ],
    "host.os.name.text": [
      "Ubuntu"
    ],
    "host.hostname": [
      "kind-control-plane"
    ],
    "host.mac": [
      "02-42-AC-12-00-02",
      "02-42-AC-13-00-04",
      "06-DD-17-EE-41-97",
      "22-F1-EB-33-1A-13",
      "66-56-4C-AB-83-C0"
    ],
    "service.type": [
      "aws"
    ],
    "host.ip": [
      "10.244.0.1",
      "10.244.0.1",
      "10.244.0.1",
      "172.18.0.2",
      "fc00:f853:ccd:e793::2",
      "fe80::42:acff:fe12:2",
      "172.19.0.4"
    ],
    "agent.type": [
      "metricbeat"
    ],
    "aws.dimensions.Class": [
      "None"
    ],
    "event.module": [
      "aws"
    ],
    "host.os.version": [
      "20.04.6 LTS (Focal Fossa)"
    ],
    "host.os.kernel": [
      "5.15.49-linuxkit"
    ],
    "host.os.name": [
      "Ubuntu"
    ],
    "aws.cloudwatch.namespace": [
      "AWS/Usage"
    ],
    "agent.name": [
      "kind-control-plane"
    ],
    "elastic_agent.snapshot": [
      true
    ],
    "host.name": [
      "kind-control-plane"
    ],
    "event.agent_id_status": [
      "verified"
    ],
    "aws.dimensions.Service": [
      "CloudWatch"
    ],
    "host.id": [
      "0aab3a64904042bdb1c956d6fe2fa4f1"
    ],
    "aws.usage.metrics.CallCount.sum": [
      40
    ],
    "cloud.region": [
      "sa-east-1"
    ],
    "host.os.type": [
      "linux"
    ],
    "cloud.account.name": [
      "elastic-observability"
    ],
    "elastic_agent.id": [
      "178edbcb-2132-497d-b6da-e8c7d8095a90"
    ],
    "data_stream.namespace": [
      "default"
    ],
    "metricset.period": [
      60000
    ],
    "aws.dimensions.Type": [
      "API"
    ],
    "host.os.codename": [
      "focal"
    ],
    "data_stream.type": [
      "metrics"
    ],
    "event.duration": [
      9720431083
    ],
    "host.architecture": [
      "x86_64"
    ],
    "metricset.name": [
      "cloudwatch"
    ],
    "cloud.provider": [
      "aws"
    ],
    "event.ingested": [
      "2023-06-29T12:21:42.000Z"
    ],
    "@timestamp": [
      "2023-06-29T12:20:00.000Z"
    ],
    "agent.id": [
      "178edbcb-2132-497d-b6da-e8c7d8095a90"
    ],
    "host.containerized": [
      false
    ],
    "ecs.version": [
      "8.0.0"
    ],
    "host.os.platform": [
      "ubuntu"
    ],
    "cloud.account.id": [
      "627286350134"
    ],
    "data_stream.dataset": [
      "aws.usage"
    ],
    "agent.ephemeral_id": [
      "e63bc826-7b49-4d1d-85f0-40340b77461d"
    ],
    "agent.version": [
      "8.8.0"
    ],
    "aws.dimensions.Resource": [
      "ListMetrics"
    ],
    "host.os.family": [
      "debian"
    ],
    "event.dataset": [
      "aws.usage"
    ]
  }
}

This issue might be hard to reproduce. When testing, I got the output: Out of 40000 documents from the index .ds-metrics-aws.usage-default-2023.06.29-000001, 429 of them were discarded., which means that this is happening with just 1% of the documents.

Metadata

Metadata

Assignees

No one assigned

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions