Docs » Integrations Guide » Integrations Reference » Disk

image0 Disk

Metadata associated with the Disk collectd plugin can be found here. The relevant code for the plugin can be found here.

DESCRIPTION

From collectdwiki:

The Disk plugin collects performance statistics of hard-disks and, where supported, partitions. While the octets and operations are quite straight forward, the other two datasets need a little explanation:

  • merged are the number of operations, that could be merged into other, already queued operations, i. e. one physical disk access served two or more logical operations. Of course, the higher that number, the better.
  • time is the average time an I/O-operation took to complete. Since this is a little messy to calculate take the actual values with a grain of salt. Since 5.5 there are also additional metrics on the Linux platform:
  • io_time - time spent doing I/Os (ms). You can treat this metric as a device load percentage (Value of 1 sec time spent matches 100% of load).
  • weighted_io_time - measure of both I/O completion time and the backlog that may be accumulating.
  • pending_operations - shows queue size of pending I/O operations. For details about these metrics you can also read kernel documentation (Explanations of fields “Field 9”, “Field 10” and “Field 11”).

REQUIREMENTS AND DEPENDENCIES

This plugin requires:

Software Version
collectd 1.5+

INSTALLATION

If you are using the new Smart Agent, see the docs for the collectd/diskmonitor for more information. The configuration documentation below may be helpful as well, but consult the Smart Agent repo’s docs for the exact schema.

Installation and initial configuration options are available as part of the SignalFx collectdagent.

CONFIGURATION

Optional configuration

The following configuration options are optional. You may specify them in the configuration file in order to override default values provided by the plugin.

configuration option definition default value
Disk Include specific Disk(s) “sda” “/^hd/”
IgnoreSelected Ignore the designation of specific Disks false

USAGE

The primary use of this plugin is to track the available space on the systems disks. This can be used to set alerts and thresholds to avoid a disks from being filled to capacity.

The SignalFx collectd plugin computes aggregated utilization metrics based on the output of this plugin you can learn more by looking at the metrics for the plugin.

METRICS

Below is a list of all metrics.

Metric Name Brief Type
derive.disk_merged.read The number of disk reads merged into single physical disk access operations. cumulative counter
derive.disk_merged.write The number of disk writes merged into single physical disk access operations. cumulative counter
derive.disk_octets.read The number of bytes (octets) read from a disk. cumulative counter
derive.disk_octets.write The number of bytes (octets) written to a disk. cumulative counter
derive.disk_ops.read The number of disk read operations. cumulative counter
derive.disk_ops.write The number of disk write operations. cumulative counter
derive.disk_time.read The average amount of time it took to do a read operation. cumulative counter
derive.disk_time.write The average amount of time it took to do a write operation. cumulative counter

derive.disk_merged.read

cumulative counter

The number of disk reads that have been merged into single physical disk access operations. In other words, this metric measures the number of instances in which one physical disk access served multiple disk reads.

derive.disk_merged.write

cumulative counter

The number of disk writes that were merged into single physical disk access operations. In other words, this metric measures the number of instances in which one physical disk access served multiple write operations.

derive.disk_octets.read

cumulative counter

The number of bytes read from a disk.

derive.disk_octets.write

cumulative counter

The number of bytes written to a disk.

derive.disk_ops.read

cumulative counter

The number of disk read operations.

derive.disk_ops.write

cumulative counter

The number of disk write operations.

derive.disk_time.read

cumulative counter

The average amount of time it took to do a read operation. For Darwin / Mac OS X, the unit is microseconds. For Linux and AIX, the unit is milliseconds. For Solaris, the unit is nanoseconds. This metric is not reported on FreeBSD.

derive.disk_time.write

cumulative counter

The average amount of time it took to do a write operation. For Darwin / Mac OS X, the unit is microseconds. For Linux and AIX, the unit is milliseconds. For Solaris, the unit is nanoseconds. This metric is not reported on FreeBSD.