6.7

Table Of Contents
Table 110. CPU Performance Enhancement Advice (Continued)
# Resolution
6 Enable CPU-saving features, such as TCP Segmentation Offload.
7 Replace software I/O with the dedicated hardware, such as iSCSI HBAs or TCP Segmentation Offload NICs.
Disk (KBps)
The Disk (KBps) chart displays the disk I/O of the 10 hosts in the cluster with the most disk usage.
This chart is located in the Hosts view of the cluster Performance tab.
Table 111. Data Counters
Chart Label Description
host_name Average data I/O rate across all hosts in the cluster.
n
Counter: usage
n
Stats Type: Rate
n
Unit: Kilobytes per second (KBps)
n
Rollup Type: Average (Minimum/Maximum)
n
Collection Level: 1 (4)
Chart Analysis
Use the disk charts to monitor average disk loads and to determine trends in disk usage. For example,
you might notice a performance degradation with applications that frequently read from and write to the
hard disk. If you see a spike in the number of disk read or write requests, check whether any such
applications were running then.
The best ways to determine if your vSphere environment is experiencing disk problems is to monitor the
disk latency data counters. You can use the advanced performance charts to view these statistics.
n
The kernelLatency data counter measures the average amount of time, in milliseconds, that the
VMkernel spends processing each SCSI command. For best performance, the value must be 0 -1
milliseconds. If the value is greater than 4 ms, the virtual machines on the host are trying to send
more throughput to the storage system than the configuration supports. Check the CPU usage, and
increase the queue depth.
n
The deviceLatency data counter measures the average amount of time, in milliseconds, to complete a
SCSI command from the physical device. Depending on your hardware, a number greater than 15 ms
indicates probable problems with the storage array. Move the active VMDK to a volume with more
spindles or add disks to the LUN.
n
The queueLatency data counter measures the average amount of time taken per SCSI command in
the VMkernel queue. This value must always be zero. If not, the workload is too high and the array
cannot process the data fast enough.
If the disk latency values are high, or if you notice other problems with disk I/O performance, consider
taking the following actions.
vSphere Monitoring and Performance
VMware, Inc. 17