Notice

This document is for a development version of Ceph.

Report a Documentation Bug

Device Management

Device management allows Ceph to address hardware failure. Ceph tracks hardware storage devices (HDDs, SSDs) to see which devices are managed by which daemons. Ceph also collects health metrics about these devices. By doing so, Ceph can provide tools that predict hardware failure and can automatically respond to hardware failure.

Device tracking

To see a list of the storage devices that are in use, run the following command:

ceph device ls

Alternatively, to list devices by daemon or by host, run a command of one of the following forms:

ceph device ls-by-daemon <daemon>
ceph device ls-by-host <host>

To see information about the location of a specific device and about how the device is being consumed, run a command of the following form:

ceph device info <devid>

Identifying physical devices

To make the replacement of failed disks easier and less error-prone, you can (in some cases) “blink” the drive’s LEDs on hardware enclosures by running a command of the following form:

ceph device light on|off <devid> [ident|fault] [--force]

Note

Using this command to blink the lights might not work. Whether it works will depend upon such factors as your kernel revision, your SES firmware, or the setup of your HBA.

The <devid> parameter is the device identification. To retrieve this information, run the following command:

ceph device ls

The [ident|fault] parameter determines which kind of light will blink. By default, the ident light is used.

Note

This command works only if the Cephadm or the Rook orchestrator module is enabled. To see which orchestrator module is enabled, run the following command:

ceph orch status

The command that makes the drive’s LEDs blink is lsmcli. To customize this command, configure it via a Jinja2 template by running commands of the following forms:

ceph config-key set mgr/cephadm/blink_device_light_cmd "<template>"
ceph config-key set mgr/cephadm/<host>/blink_device_light_cmd "lsmcli local-disk-{{ ident_fault }}-led-{{'on' if on else 'off'}} --path '{{ path or dev }}'"

The following arguments can be used to customize the Jinja2 template:

• on: A Boolean value.

• ident_fault: A string that contains ident or fault.

• dev: The kernel name of the device on its host, for example sda.

• path: The device’s link under /dev/disk/by-path, if the Manager has recorded one. Otherwise this is an empty string, and the default template, {{ path or dev }}, uses dev instead.

Enabling monitoring

Ceph can also monitor the health metrics associated with your device. For example, SATA drives implement a standard called SMART that provides a wide range of internal metrics about the device’s usage and health (for example: the number of hours powered on, the number of power cycles, the number of unrecoverable read errors). Other device types such as SAS and NVMe present a similar set of metrics (via slightly different standards). All of these metrics can be collected by Ceph via the smartctl tool.

You can enable or disable health monitoring by running one of the following commands:

ceph device monitoring on
ceph device monitoring off

Scraping

If monitoring is enabled, device metrics will be scraped automatically at regular intervals. To configure that interval, run a command of the following form:

ceph config set mgr mgr/devicehealth/scrape_frequency <seconds>

By default, device metrics are scraped once every 24 hours.

To manually scrape all devices, run the following command:

ceph device scrape-health-metrics

To scrape a single device, run a command of the following form:

ceph device scrape-health-metrics <device-id>

To scrape a single daemon’s devices, run a command of the following form:

ceph device scrape-daemon-health-metrics <who>

To retrieve the stored health metrics for a device (optionally for a specific timestamp), run a command of the following form:

ceph device get-health-metrics <devid> [sample-timestamp]

Failure prediction

Ceph can predict drive life expectancy and device failures by analyzing the health metrics that it collects. The prediction modes are as follows:

• none: disable device failure prediction. This is the default.

• local: use a pre-trained prediction model from the diskprediction_local Manager module.

The local mode works only when the diskprediction_local module is enabled. To use it, run the following commands:

ceph mgr module enable diskprediction_local
ceph config set global device_failure_prediction_mode local

In the local mode, failure prediction runs periodically in the background. The predictor runs once a day, and it needs at least six sets of health metrics for a device (six days at the default scrape interval) before it can estimate that device’s life expectancy. For this reason, life expectancy values might be populated only after a significant amount of time has passed. See Diskprediction Module.

The life expectancy of all devices is displayed in the output of the following command:

ceph device ls

To see the metadata of a specific device, run a command of the following form:

ceph device info <devid>

To print the local predictor’s estimate for a single device (>6w, >=2w and <=6w, <2w, or unknown), run a command of the following form. It works only in the local mode, and it does not change the stored life expectancy that ceph device ls shows:

ceph device predict-life-expectancy <devid>

In addition to Ceph’s internal device failure prediction, you might have an external source of information about device failures. To inform Ceph of a specific device’s life expectancy, run a command of the following form:

ceph device set-life-expectancy <devid> <from> [<to>]

Life expectancies are expressed as a time interval. This means that the uncertainty of the life expectancy can be expressed in the form of a range of time, and perhaps a wide range of time. The interval’s end can be left unspecified, but then Ceph neither raises DEVICE_HEALTH for the device nor marks its OSDs out.

Health alerts

The mgr/devicehealth/warn_threshold option (default 12 weeks) controls the DEVICE_HEALTH health check. The Manager raises it when the end of a device’s life expectancy interval is closer than this threshold.

To check the stored life expectancy of all devices now, raise any appropriate health alerts, and (when mgr/devicehealth/self_heal is enabled) mark out the OSDs on devices that are expected to fail within mgr/devicehealth/mark_out_threshold, run the following command:

ceph device check-health

Automatic Migration

The mgr/devicehealth/self_heal option (enabled by default) automatically migrates data away from devices that are expected to fail soon. If this option is enabled, the module marks the OSDs that use such devices out and sets their primary affinity to 0, so that automatic migration will occur.

Note

The mon_osd_min_in_ratio option prevents this process from cascading to total failure. The module does not mark an OSD out if that would bring the ratio of in OSDs below mon_osd_min_in_ratio. Instead, the cluster raises the DEVICE_HEALTH_TOOMANY health check. For instructions on what to do in this situation, see DEVICE_HEALTH_TOOMANY.

The mgr/devicehealth/mark_out_threshold option (default 4 weeks) controls automatic migration. When mgr/devicehealth/self_heal is enabled, the Manager marks out the OSDs on any device whose life expectancy interval ends closer than this threshold.

Brought to you by the Ceph Foundation

The Ceph Documentation is a community resource funded and hosted by the non-profit Ceph Foundation. If you would like to support this and our other efforts, please consider joining now.