eG Monitoring
 

Measures reported by NutAHVStorageTest

Nutanix combines compute(CPU) resources with storage resources delivered via SSDs and directly-attached (DAS) SATA HDD media drives. The VMs operating on the Nutanix Acropolis hypervisor use these aggregated storage resources for their operations. The lack of adequate, well-tuned storage resources can therefore severely impair VM operations and availability. To avoid this, a Nutanix administrator has to continuously measure overall storage performance and accurately determine the following:

  • How is the I/O load on the storage?

  • Is the storage processing I/O requests quickly?

  • Is too much bandwidth being consumed when processing I/O?

  • Is the AHV sized with adequate storage resources? If not, what type of storage is running short of space - the SSDs? or the SATA HDDs?

This test helps administrators monitor overall storage health and rapidly leads them to the problem areas by providing quick and accurate answers to the aforesaid.

The measures made by this test are as follows:

Measurement Description Measurement Unit Interpretation
IO_LATENCY Indicates the average time taken by the storage to process I/O requests. Seconds Ideally, the value of this measure should be very low. A high value or a steady increase in this value could indicate an I/O processing bottleneck on the storage. In such a case, compare the value of the READ_LATENCY and WRITE_LATENCY measures to figure out when the slowness is worst - when processing read requests? or write requests?
READ_LATENCY Indicates the average time taken by the storage to process read I/O requests. Seconds If the IO_LATENCY measure reports an abnormally high value, then compare the value of these measures to figure out where the slowness is maximum - when processing read requests? or write requests?
WRITE_LATENCY Indicates the average time taken by the storage to process write I/O requests. Seconds
IO_BANDWIDTH Indicates the bandwidth per second used by the storage when processing I/O requests. KB/Sec A high value for this measure denotes that the storage is processing bandwidth-intensive I/O. In such situations, you may want to compare the value of the READ_BANDWIDTH and WRITE_BANDWIDTH measures to know what type of I/O requests are truly contributing to the excessive bandwidth consumptions - read requests? or write requests?
READ_BANDWIDTH Indicates the bandwidth per second used by the storage when processing read I/O requests. KB/Sec If the value of the IO_BANDWIDTH measure is high, then you may want to compare the values of these measures to know what type of I/O requests are truly contributing to the excessive bandwidth consumption - read requests? or write requests?
WRITE_BANDWIDTH Indicates the bandwidth per second used by the storage when processing write I/O requests. KB/Sec
NUM_IOPS Indicates the number of I/O operations performed currently on the storage. Number If the value of the NUM_IOPS measure is unusually high, then compare the value of these measures to know what is contributing to the unusual I/O activity levels - read requests? or write requests?
READ_IOPS Indicates the number of read I/O operations performed currently on the storage. Number If the value of the NUM_IOPS measure is unusually high, then compare the value of these measures to know what is contributing to the unusual I/O activity levels - read requests? or write requests?
WRITE_IOPS Indicates the number of write I/O operations performed currently on the container. Number
STORAGE_CAPACITY Indicates the total storage capacity. GB  
STORAGE_USED Indicates the amount of storage space used by the monitored hypervisor and its VMs. GB A low value is desired for this measure.
STORAGE_FREE Indicates the amount of storage space that is still unused. GB CA high value is desired for this measure.
STORAGE_UPERC Indicates the percentage of storage capacity currently in use. Percent A value close to 100% indicates that the storage resources are being depleted rapidly. To know what type of storage resources are being over-utilized, compare the value of the SSD disk space usage and DAS-SATA disk space usage measures of this test.
STORAGE_FPERC Indicates of percentage of storage capacity that is currently free and available for use. Percent A value less than 50% indicates that the storage resources are being depleted rapidly. To know what type of storage resources are being over-utilized, compare the value of the SSD disk space usage and DAS-SATA disk space usage measures of this test.
STORAGE_LUSAGE Indicates the amount of logical storage space that is in use currently. GB  
SSD_CAPACITY Indicates the total storage capacity across all SSDs. GB  
SSD_USAGE Indicates the amount of storage space used by all SSDs. GB A low value is desired for this measure.
SSD_FREE Indicates the amount of storage space that is still unused in the SSDs. GB A high value is desired for this measure.
SSD_FREE_PERC Indicates of percentage of SSD storage capacity that is currently free and available for use. Percent A value less than 50% indicates that the storage space in the SSDs is being depleted rapidly.
DAS_CAPACITY Indicates the total storage capacity across all directly attached SATA HDDs. GB  
DAS_USAGE Indicates the total amount of storage space used by all directly attached SATA HDDs. GB A low value is desired for this measure.
DAS_FREE Indicates the amount of storage space that is still unused in the directly attached SATA HDDs. GB A high value is desired for this measure.
DAS_USE_PERC Indicates the percentage of the storage capacity of directly attached SATA HDDs that is currently in use. Percent A value close to 100% indicates that the storage space in the HDDs is being depleted rapidly.
DAS_FREE_PERC Indicates of percentage of the storage capacity of directly attached SATA HDDs that is currently free and available for use. Percent A value less than 50% indicates that the storage space in the HDDs is being depleted rapidly.