Monitors the Physical Disk read and write latency (average disk seconds per transfer).
The Avg. Disk sec/Transfer (PhysicalDisk\Avg. Disk sec/Transfer) for the physical disk has exceeded the threshold. The physical disk and possibly even overall system performance may significantly diminish which will result in poor operating system and application performance.
The Avg. Disk sec/Transfer counter measures the average time of data reads and writes on the disk.
The Avg. Disk sec/ Transfer counter is made up from both read and write disk Transfer requests. To view recent disk average rate of read and write Transfer requests you can use the following views:
Physical Disk\Avg. Disk Sec/Reads Performance View
Physical Disk\Avg. Disk Sec/Writes Performance View
A high Avg. Disk sec/Transfer performance counter value may occur due to a burst of disk transfer requests by either an operating system or application.
To view recent history for the Physical Disk\Avg. Disk sec/Transfers performance counter you can use the following view:
Start Physical Disk Performance View
To increase the available storage subsystem throughput for this physical disk, do one or more of the following:
Upgrade the controllers or disk drives.
Switch from RAID-5 to RAID-0+1.
Increase the number of actual spindles.
Be sure to set this threshold value appropriately for your specific storage hardware. The threshold value will vary according to the disk’s underlying storage subsystem. For example, the “disk” might be a single spindle or a large disk array. You can use MOM overrides to define exception thresholds, which can be applied to specific computers or entire computer groups.
The Avg. Disk sec/Transfer counter is useful in gathering throughput data. If the average time is long enough, you can analyze a histogram of the array’s response to specific loads (queues, request sizes, and so on). If possible, you should observe workloads separately.
You can use throughput metrics to determine:
1. The behavior of a workload running on a given host system. You can track the workload requirements for disk transfer requests over time. Characterization of workloads is an important part of performance analysis and capacity planning.
2. The peak and sustainable levels of performance that are provided by a given storage subsystem. A workload can either be used to artificially or naturally push a storage subsystem (in this case, a given physical disk) to its limits. Determining these limits provides useful configuration information for system designers and administrators.
However, without thorough knowledge of the underlying storage subsystem of the physical disk (for example, knowing whether it is a single spindle or a massive disk array), it can be difficult to provide an optimized one size fits all threshold value.
You must also consider the Avg. Disk sec/Transfer counter in conjunction with other transfer request characteristics (for example, request size and randomness/sequentially) and the equivalent counters for write disk requests.
If the Avg. Disk sec/Transfers counter is tracked over time and if it increases with the intensity of the workloads that are driving the transfer requests, it is reasonable to suspect that the physical disk is saturated if throughput does not increase and the user experiences degraded system throughput.
For more information about storage architecture and driver support, see the Storage - Architecture and Driver Support Web site at http://go.microsoft.com/fwlink/?LinkId=26156.
Target | Microsoft.Windows.Server.2008.PhysicalDisk | ||
Parent Monitor | System.Health.PerformanceState | ||
Category | PerformanceHealth | ||
Enabled | True | ||
Instance Name | PhysicalDisk | ||
Counter Name | Avg. Disk sec/Transfer | ||
Frequency | 60 | ||
Alert Generate | True | ||
Alert Severity | Warning | ||
Alert Priority | Normal | ||
Alert Auto Resolve | True | ||
Monitor Type | System.Performance.ConsecutiveSamplesThreshold | ||
Remotable | True | ||
Accessibility | Public | ||
Alert Message |
| ||
RunAs | Default |
<UnitMonitor ID="Microsoft.Windows.Server.2008.PhysicalDisk.AvgDiskSecPerTransfer" Accessibility="Public" Enabled="true" Target="Server2008!Microsoft.Windows.Server.2008.PhysicalDisk" ParentMonitorID="SystemHealth!System.Health.PerformanceState" Remotable="true" Priority="Normal" TypeID="SystemPerf!System.Performance.ConsecutiveSamplesThreshold" ConfirmDelivery="false">
<Category>PerformanceHealth</Category>
<AlertSettings AlertMessage="Microsoft.Windows.Server.2008.PhysicalDisk.AvgDiskSecPerTransfer.AlertMessage">
<AlertOnState>Warning</AlertOnState>
<AutoResolve>true</AutoResolve>
<AlertPriority>Normal</AlertPriority>
<AlertSeverity>Warning</AlertSeverity>
<AlertParameters/>
</AlertSettings>
<OperationalStates>
<OperationalState ID="OverThreshold" MonitorTypeStateID="ConditionTrue" HealthState="Warning"/>
<OperationalState ID="UnderThreshold" MonitorTypeStateID="ConditionFalse" HealthState="Success"/>
</OperationalStates>
<Configuration>
<ComputerName>$Target/Host/Property[Type="Windows!Microsoft.Windows.Computer"]/NetworkName$</ComputerName>
<CounterName>Avg. Disk sec/Transfer</CounterName>
<ObjectName>PhysicalDisk</ObjectName>
<InstanceName>$Target/Property[Type="WindowsServer!Microsoft.Windows.Server.PhysicalDisk"]/PerfmonInstance$</InstanceName>
<Frequency>60</Frequency>
<Threshold>0.04</Threshold>
<Direction>greater</Direction>
<NumSamples>15</NumSamples>
</Configuration>
</UnitMonitor>