Disk Metrics
Reference information for Disk Metrics
In addition to these base metrics, many aggregate metrics are available.
If an entity type has parents defined, you can formulate all possible
aggregate metrics using the formula
base_metric_across_parents.
In addition, metrics for aggregate totals can be formed by adding the prefix
total_ to the front of the metric name.
Use the type-ahead feature in the Cloudera Manager chart browser to find the exact aggregate metric name, in case the plural form does not end in "s".
For example, the following metric names may be valid for Disk:
-
average_queue_length_across_clusters -
total_average_queue_length_across_clusters
Some metrics, such as alerts_rate, apply to nearly every metric context. Others only apply to a
certain service or role.
average_queue_length
- Description
- The average queue length of the requests issued to the disk. This is the same as the 'avgqu-sz' measure from iostat.
- Unit
- ios
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
average_request_size
- Description
- The average size in sectors of the requests issued to the disk. This is the same as the 'avgrq-sz' measure from iostat.
- Unit
- sectors
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
await_read_time
- Description
- The average time for read requests issued to the disk to be served. This includes the time spent by the requests in queue and the time spent servicing them. This is the same as the 'r_await' measure from iostat.
- Unit
- ms
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
await_time
- Description
- The average time for requests issued to the disk to be served. This includes the time spent by the requests in queue and the time spent servicing them. This is the same as the 'await' measure from iostat.
- Unit
- ms
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
await_write_time
- Description
- The average time for write requests issued to the disk to be served. This includes the time spent by the requests in queue and the time spent servicing them. This is the same as the 'w_await' measure from iostat.
- Unit
- ms
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
read_bytes_rate
- Description
- The number of bytes read from the device
- Unit
- bytes per second
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
read_ios_rate
- Description
- The number of read I/O operations issued to the device
- Unit
- ios per second
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
service_time
- Description
- The average service time for requests issued to the disk. This is the same as the 'svctm' measure from iostat. Note the warning from iostat for this metric: Warning! Do not trust this field any more. This field will be removed in a future sysstat version.
- Unit
- ms
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
utilization
- Description
- The percentage of CPU time during which I/O requests were issued to the device. This is the same as the 'util' measure from iostat.
- Unit
- percent
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
write_bytes_rate
- Description
- The number of bytes written to the device
- Unit
- bytes per second
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
write_ios_rate
- Description
- The number of write I/O operations issued to the device
- Unit
- ios per second
- Parents
- cluster, host, rack
- CDH Version
- [CM -1.0.0..CM -1.0.0]
