github.com/netdata/go.d.plugin@v0.58.1/modules/nvme/metadata.yaml (about)

     1  plugin_name: go.d.plugin
     2  modules:
     3    - meta:
     4        id: collector-go.d.plugin-nvme
     5        plugin_name: go.d.plugin
     6        module_name: nvme
     7        monitored_instance:
     8          name: NVMe devices
     9          link: ""
    10          icon_filename: nvme.svg
    11          categories:
    12            - data-collection.storage-mount-points-and-filesystems
    13        keywords:
    14          - nvme
    15        related_resources:
    16          integrations:
    17            list: []
    18        info_provided_to_referring_integrations:
    19          description: ""
    20        most_popular: false
    21      overview:
    22        data_collection:
    23          metrics_description: >
    24            This collector monitors the health of NVMe devices using the command line
    25            tool [nvme](https://github.com/linux-nvme/nvme-cli#nvme-cli), which can only be run by the root user. It uses `sudo` and
    26            assumes it is set up so that the netdata user can execute `nvme` as root without a password.
    27          method_description: ""
    28        supported_platforms:
    29          include: []
    30          exclude: []
    31        multi_instance: true
    32        additional_permissions:
    33          description: ""
    34        default_behavior:
    35          auto_detection:
    36            description: ""
    37          limits:
    38            description: ""
    39          performance_impact:
    40            description: ""
    41      setup:
    42        prerequisites:
    43          list:
    44            - title: Install nvme-cli
    45              description: |
    46                See [Distro Support](https://github.com/linux-nvme/nvme-cli#distro-support). Install `nvme-cli` using your distribution's package manager.
    47            - title: Allow netdata to execute nvme
    48              description: |
    49                Add the netdata user to `/etc/sudoers` (use `which nvme` to find the full path to the binary):
    50  
    51                ```bash
    52                netdata ALL=(root) NOPASSWD: /usr/sbin/nvme
    53                ```
    54        configuration:
    55          file:
    56            name: go.d/nvme.conf
    57          options:
    58            description: |
    59              The following options can be defined globally: update_every, autodetection_retry.
    60            folding:
    61              title: Config options
    62              enabled: true
    63            list:
    64              - name: update_every
    65                description: Data collection frequency.
    66                default_value: 10
    67                required: false
    68              - name: autodetection_retry
    69                description: Recheck interval in seconds. Zero means no recheck will be scheduled.
    70                default_value: 0
    71                required: false
    72              - name: binary_path
    73                description: Path to nvme binary. The default is "nvme" and the executable is looked for in the directories specified in the PATH environment variable.
    74                default_value: nvme
    75                required: false
    76              - name: timeout
    77                description: nvme binary execution timeout.
    78                default_value: 2
    79                required: false
    80          examples:
    81            folding:
    82              title: Config
    83              enabled: true
    84            list:
    85              - name: Custom binary path
    86                description: The executable is not in the directories specified in the PATH environment variable.
    87                config: |
    88                  jobs:
    89                    - name: nvme
    90                      binary_path: /usr/local/sbin/nvme
    91      troubleshooting:
    92        problems:
    93          list: []
    94      alerts:
    95        - name: nvme_device_critical_warnings_state
    96          metric: nvme.device_critical_warnings_state
    97          info: "NVMe device ${label:device} has critical warnings"
    98          link: https://github.com/netdata/netdata/blob/master/src/health/health.d/nvme.conf
    99      metrics:
   100        folding:
   101          title: Metrics
   102          enabled: false
   103        description: ""
   104        availability: []
   105        scopes:
   106          - name: device
   107            description: These metrics refer to the NVME device.
   108            labels:
   109              - name: device
   110                description: NVMe device name
   111            metrics:
   112              - name: nvme.device_estimated_endurance_perc
   113                description: Estimated endurance
   114                unit: '%'
   115                chart_type: line
   116                dimensions:
   117                  - name: used
   118              - name: nvme.device_available_spare_perc
   119                description: Remaining spare capacity
   120                unit: '%'
   121                chart_type: line
   122                dimensions:
   123                  - name: spare
   124              - name: nvme.device_composite_temperature
   125                description: Composite temperature
   126                unit: celsius
   127                chart_type: line
   128                dimensions:
   129                  - name: temperature
   130              - name: nvme.device_io_transferred_count
   131                description: Amount of data transferred to and from device
   132                unit: bytes
   133                chart_type: area
   134                dimensions:
   135                  - name: read
   136                  - name: written
   137              - name: nvme.device_power_cycles_count
   138                description: Power cycles
   139                unit: cycles
   140                chart_type: line
   141                dimensions:
   142                  - name: power
   143              - name: nvme.device_power_on_time
   144                description: Power-on time
   145                unit: seconds
   146                chart_type: line
   147                dimensions:
   148                  - name: power-on
   149              - name: nvme.device_critical_warnings_state
   150                description: Critical warnings state
   151                unit: state
   152                chart_type: line
   153                dimensions:
   154                  - name: available_spare
   155                  - name: temp_threshold
   156                  - name: nvm_subsystem_reliability
   157                  - name: read_only
   158                  - name: volatile_mem_backup_failed
   159                  - name: persistent_memory_read_only
   160              - name: nvme.device_unsafe_shutdowns_count
   161                description: Unsafe shutdowns
   162                unit: shutdowns
   163                chart_type: line
   164                dimensions:
   165                  - name: unsafe
   166              - name: nvme.device_media_errors_rate
   167                description: Media and data integrity errors
   168                unit: errors/s
   169                chart_type: line
   170                dimensions:
   171                  - name: media
   172              - name: nvme.device_error_log_entries_rate
   173                description: Error log entries
   174                unit: entries/s
   175                chart_type: line
   176                dimensions:
   177                  - name: error_log
   178              - name: nvme.device_warning_composite_temperature_time
   179                description: Warning composite temperature time
   180                unit: seconds
   181                chart_type: line
   182                dimensions:
   183                  - name: wctemp
   184              - name: nvme.device_critical_composite_temperature_time
   185                description: Critical composite temperature time
   186                unit: seconds
   187                chart_type: line
   188                dimensions:
   189                  - name: cctemp
   190              - name: nvme.device_thermal_mgmt_temp1_transitions_rate
   191                description: Thermal management temp1 transitions
   192                unit: transitions/s
   193                chart_type: line
   194                dimensions:
   195                  - name: temp1
   196              - name: nvme.device_thermal_mgmt_temp2_transitions_rate
   197                description: Thermal management temp2 transitions
   198                unit: transitions/s
   199                chart_type: line
   200                dimensions:
   201                  - name: temp2
   202              - name: nvme.device_thermal_mgmt_temp1_time
   203                description: Thermal management temp1 time
   204                unit: seconds
   205                chart_type: line
   206                dimensions:
   207                  - name: temp1
   208              - name: nvme.device_thermal_mgmt_temp2_time
   209                description: Thermal management temp2 time
   210                unit: seconds
   211                chart_type: line
   212                dimensions:
   213                  - name: temp2