kube-arangodb/internal/metrics.yaml

documentation: docs/generated/metrics
destination: pkg/generated/metric_descriptions
namespaces:
  arangodb_operator:
    agency_cache:
      present:
        shortDescription: "Determines if local agency cache is present"
        description: "Determines if local agency cache is present"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      health_present:
        shortDescription: "Determines if local agency cache health is present"
        description: "Determines if local agency cache health is present"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      serving:
        shortDescription: "Determines if agency is serving"
        description: "Determines if agency is serving"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      healthy:
        shortDescription: "Determines if agency is healthy"
        description: "Determines if agency is healthy"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      member_serving:
        shortDescription: "Determines if agency member is reachable"
        description: "Determines if agency member is reachable"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
          - key: agent
            description: "Agent ID"
      member_commit_offset:
        shortDescription: "Determines agency member commit offset"
        description: "Determines agency member commit offset. Set to -1 if Agent is not reachable"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
          - key: agent
            description: "Agent ID"
      leaders:
        shortDescription: "Determines agency leader vote count"
        description: "Determines agency leader vote count. Should be always one"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
          - key: agent
            description: "Agent ID"
    agency:
      index:
        shortDescription: "Current index of the agency cache"
        description: "Current index of the agency cache"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      fetches:
        shortDescription: "Current count of agency cache fetches"
        description: "Current count of agency cache fetches"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      errors:
        shortDescription: "Current count of agency cache fetch errors"
        description: "Current count of agency cache fetch errors"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
    rebalancer:
      enabled:
        shortDescription: "Determines if rebalancer is enabled"
        description: "Determines if rebalancer is enabled"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      moves_generated:
        shortDescription: "Define how many moves were generated"
        description: "Define how many moves were generated"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      moves_succeeded:
        shortDescription: "Define how many moves succeeded"
        description: "Define how many moves succeeded"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      moves_failed:
        shortDescription: "Define how many moves failed"
        description: "Define how many moves failed"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      moves_current:
        shortDescription: "Define how many moves are currently in progress"
        description: "Define how many moves are currently in progress"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
    resources:
      arangodeployment_status_restores:
        shortDescription: "Counter for deployment status restored"
        description: "Counter for deployment status restored"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      arangodeployment_validation_errors:
        shortDescription: "Counter for deployment validation errors"
        description: "Counter for deployment validation errors"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      arangodeployment_immutable_errors:
        shortDescription: "Counter for deployment immutable errors"
        description: "Counter for deployment immutable errors"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      arangodeployment_accepted:
        shortDescription: "Defines if ArangoDeployment has been accepted"
        description: "Defines if ArangoDeployment has been accepted"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      arangodeployment_propagated:
        shortDescription: "Defines if ArangoDeployment Spec is propagated"
        description: "Defines if ArangoDeployment Spec is propagated"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      arangodeployment_uptodate:
        shortDescription: "Defines if ArangoDeployment is uptodate"
        description: "Defines if ArangoDeployment is uptodate"
        type: "Gauge"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
      arangodeploymentreplication_active:
        shortDescription: "Defines if ArangoDeploymentReplication is configured and running"
        description: "Defines if ArangoDeploymentReplication is configured and running"
        type: "Gauge"
        labels:
          - key: namespace
            description: "DeploymentReplication Namespace"
          - key: name
            description: "DeploymentReplication Name"
      arangodeploymentreplication_failed:
        shortDescription: "Defines if ArangoDeploymentReplication is in Failed phase"
        description: "Defines if ArangoDeploymentReplication is in Failed phase"
        type: "Gauge"
        labels:
          - key: namespace
            description: "DeploymentReplication Namespace"
          - key: name
            description: "DeploymentReplication Name"
    members:
      unexpected_container_exit_codes:
        shortDescription: "Counter of unexpected restarts in pod (Containers/InitContainers/EphemeralContainers)"
        description: "Counter of unexpected restarts in pod (Containers/InitContainers/EphemeralContainers)"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
          - key: member
            description: "Member ID"
          - key: container
            description: "Container Name"
          - key: container_type
            description: "Container/InitContainer/EphemeralContainer"
          - key: code
            description: "ExitCode"
          - key: reason
            description: "Reason"
    engine:
      panics_recovered:
        shortDescription: "Number of Panics recovered inside Operator reconciliation loop"
        description: "Number of Panics recovered inside Operator reconciliation loop. Section represents recovery section"
        type: "Counter"
        labels:
          - key: section
            description: "Panic Section"
      assertions:
        shortDescription: "Number of assertions invoked during Operator runtime"
        description: "Number of assertions invoked during Operator runtime"
        type: "Counter"
        labels:
          - key: key
            description: "Assertion Key"
        alertingRules:
          - priority: Warning
            query: irate(arangodb_operator_engine_assertions[1m]) > 1
            description: "Trigger an alert if OPS attention is needed"
      ops_alerts:
        shortDescription: "Counter for actions which requires ops attention"
        description: "Counter for actions which requires ops attention"
        type: "Counter"
        labels:
          - key: namespace
            description: "Deployment Namespace"
          - key: name
            description: "Deployment Name"
        alertingRules:
          - priority: Warning
            query: irate(arangodb_operator_engine_ops_alerts[1m]) > 1
            description: "Trigger an alert if OPS attention is needed"
    kubernetes_client:
      requests:
        shortDescription: "Number of Kubernetes Client requests"
        description: "Number of Kubernetes Client requests"
        type: "Counter"
        labels:
          - key: component
            description: "K8S Resource name"
          - key: verb
            description: "Verb (create,update,update-status,patch,delete,force-delete)"
      request_errors:
        shortDescription: "Number of Kubernetes Client request errors"
        description: "Number of Kubernetes Client request errors"
        type: "Counter"
        labels:
          - key: component
            description: "K8S Resource name"
          - key: verb
            description: "Verb (create,update,update-status,patch,delete,force-delete)"