netdata/collectors/python.d.plugin/riakkv/metadata.yaml

plugin_name: python.d.plugin
modules:
  - meta:
      plugin_name: python.d.plugin
      module_name: riakkv
      monitored_instance:
        name: RiakKV
        link: "https://riak.com/products/riak-kv/index.html"
        categories:
          - data-collection.database-servers
        icon_filename: "riak.svg"
      related_resources:
        integrations:
          list: []
      info_provided_to_referring_integrations:
        description: ""
      keywords:
        - database
        - nosql
        - big data
      most_popular: false
    overview:
      data_collection:
        metrics_description: |
          This collector monitors RiakKV metrics about throughput, latency, resources and more.'
        method_description: "This collector reads the database stats from the `/stats` endpoint."
      supported_platforms:
        include: []
        exclude: []
      multi_instance: true
      additional_permissions:
        description: ""
      default_behavior:
        auto_detection:
          description: "If the /stats endpoint is accessible, RiakKV instances on the local host running on port 8098 will be autodetected."
        limits:
          description: ""
        performance_impact:
          description: ""
    setup:
      prerequisites:
        list:
          - title: Configure RiakKV to enable /stats endpoint
            description: |
              You can follow the RiakKV configuration reference documentation for how to enable this.
              
              Source : https://docs.riak.com/riak/kv/2.2.3/configuring/reference/#client-interfaces
      configuration:
        file:
          name: "python.d/riakkv.conf"
        options:
          description: |
            There are 2 sections:
            
            * Global variables
            * One or more JOBS that can define multiple different instances to monitor.
            
            The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values.
            
            Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition.
            
            Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified.
          folding:
            title: "Config options"
            enabled: true
          list:
            - name: update_every
              description: Sets the default data collection frequency.
              default_value: 5
              required: false
            - name: priority
              description: Controls the order of charts at the netdata dashboard.
              default_value: 60000
              required: false
            - name: autodetection_retry
              description: Sets the job re-check interval in seconds.
              default_value: 0
              required: false
            - name: penalty
              description: Indicates whether to apply penalty to update_every in case of failures.
              default_value: yes
              required: false
            - name: url
              description: The url of the server
              default_value: no
              required: true
        examples:
          folding:
            enabled: true
            title: "Config"
          list:
            - name: Basic (default)
              folding:
                enabled: false
              description: A basic example configuration per job
              config: |
                local:
                url: 'http://localhost:8098/stats'
            - name: Multi-instance
              description: |
                > **Note**: When you define multiple jobs, their names must be unique.
                
                Collecting metrics from local and remote instances.
              config: |
                local:
                  url: 'http://localhost:8098/stats'
                
                remote:
                  url: 'http://192.0.2.1:8098/stats'
    troubleshooting:
      problems:
        list: []
    alerts:
      - name: riakkv_1h_kv_get_mean_latency
        link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
        metric: riak.kv.latency.get
        info: average time between reception of client GET request and subsequent response to client over the last hour
      - name: riakkv_kv_get_slow
        link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
        metric: riak.kv.latency.get
        info: average time between reception of client GET request and subsequent response to the client over the last 3 minutes, compared to the average over the last hour
      - name: riakkv_1h_kv_put_mean_latency
        link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
        metric: riak.kv.latency.put
        info: average time between reception of client PUT request and subsequent response to the client over the last hour
      - name: riakkv_kv_put_slow
        link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
        metric: riak.kv.latency.put
        info: average time between reception of client PUT request and subsequent response to the client over the last 3 minutes, compared to the average over the last hour
      - name: riakkv_vm_high_process_count
        link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
        metric: riak.vm
        info: number of processes running in the Erlang VM
      - name: riakkv_list_keys_active
        link: https://github.com/netdata/netdata/blob/master/health/health.d/riakkv.conf
        metric: riak.core.fsm_active
        info: number of currently running list keys finite state machines
    metrics:
      folding:
        title: Metrics
        enabled: false
      description: ""
      availability: []
      scopes:
        - name: global
          description: "These metrics refer to the entire monitored application."
          labels: []
          metrics:
            - name: riak.kv.throughput
              description: Reads & writes coordinated by this node
              unit: "operations/s"
              chart_type: line
              dimensions:
                - name: gets
                - name: puts
            - name: riak.dt.vnode_updates
              description: Update operations coordinated by local vnodes by data type
              unit: "operations/s"
              chart_type: line
              dimensions:
                - name: counters
                - name: sets
                - name: maps
            - name: riak.search
              description: Search queries on the node
              unit: "queries/s"
              chart_type: line
              dimensions:
                - name: queries
            - name: riak.search.documents
              description: Documents indexed by search
              unit: "documents/s"
              chart_type: line
              dimensions:
                - name: indexed
            - name: riak.consistent.operations
              description: Consistent node operations
              unit: "operations/s"
              chart_type: line
              dimensions:
                - name: gets
                - name: puts
            - name: riak.kv.latency.get
              description: Time between reception of a client GET request and subsequent response to client
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.kv.latency.put
              description: Time between reception of a client PUT request and subsequent response to client
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.dt.latency.counter_merge
              description: Time it takes to perform an Update Counter operation
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.dt.latency.set_merge
              description: Time it takes to perform an Update Set operation
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.dt.latency.map_merge
              description: Time it takes to perform an Update Map operation
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.search.latency.query
              description: Search query latency
              unit: "ms"
              chart_type: line
              dimensions:
                - name: median
                - name: min
                - name: "95"
                - name: "99"
                - name: "999"
                - name: max
            - name: riak.search.latency.index
              description: Time it takes Search to index a new document
              unit: "ms"
              chart_type: line
              dimensions:
                - name: median
                - name: min
                - name: "95"
                - name: "99"
                - name: "999"
                - name: max
            - name: riak.consistent.latency.get
              description: Strongly consistent read latency
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.consistent.latency.put
              description: Strongly consistent write latency
              unit: "ms"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.vm
              description: Total processes running in the Erlang VM
              unit: "total"
              chart_type: line
              dimensions:
                - name: processes
            - name: riak.vm.memory.processes
              description: Memory allocated & used by Erlang processes
              unit: "MB"
              chart_type: line
              dimensions:
                - name: allocated
                - name: used
            - name: riak.kv.siblings_encountered.get
              description: Number of siblings encountered during GET operations by this node during the past minute
              unit: "siblings"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.kv.objsize.get
              description: Object size encountered by this node during the past minute
              unit: "KB"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.search.vnodeq_size
              description: Number of unprocessed messages in the vnode message queues of Search on this node in the past minute
              unit: "messages"
              chart_type: line
              dimensions:
                - name: mean
                - name: median
                - name: "95"
                - name: "99"
                - name: "100"
            - name: riak.search.index
              description: Number of document index errors encountered by Search
              unit: "errors"
              chart_type: line
              dimensions:
                - name: errors
            - name: riak.core.protobuf_connections
              description: Protocol buffer connections by status
              unit: "connections"
              chart_type: line
              dimensions:
                - name: active
            - name: riak.core.repairs
              description: Number of repair operations this node has coordinated
              unit: "repairs"
              chart_type: line
              dimensions:
                - name: read
            - name: riak.core.fsm_active
              description: Active finite state machines by kind
              unit: "fsms"
              chart_type: line
              dimensions:
                - name: get
                - name: put
                - name: secondary index
                - name: list keys
            - name: riak.core.fsm_rejected
              description: Finite state machines being rejected by Sidejobs overload protection
              unit: "fsms"
              chart_type: line
              dimensions:
                - name: get
                - name: put
            - name: riak.search.index
              description: Number of writes to Search failed due to bad data format by reason
              unit: "writes"
              chart_type: line
              dimensions:
                - name: bad_entry
                - name: extract_fail