Tuesday, July 21, 2009

Hard Drive Access Time

Hard Drive Latency

Mechanical latencies, measured in milliseconds, include both seek time and rotational latency. "Seek Time" is measured defines the amount of time it takes a hard drive's read/write head to find the physical location of a piece of data on the disk. "Latency" is the average time for the sector being accessed to rotate into position under a head, after a completed seek. It is easily calculated from the spindle speed, being the time for half a rotation. A drive's "average access time" is the interval between the time a request for data is made by the system and the time the data is available from the drive. Access time includes the actual seek time, rotational latency, and command processing overhead time.

Collected From: http://www.pctechguide.com/31HardDisk_Performance.htm

Monday, July 20, 2009

Windows Performance Monitor

Launch the process you want to monitor
Launch Perfmon
Left-hand pane, expand Performance Logs and Alerts, select Counter Logs
Right-click in right-hand pane, select New Log Settings & give it a name
Click Add Counters
Select Performance object: Process
Make your select of counter(s) & instance(s) - your process should be listed as an instance

Hint: Even if I want information on a specific process, I tend to select All counters and All instances, then just filter when I come to review the information

Click Add, then Close
Set your sample interval to suit (default is 1 per 15 seconds)

Click OK (and again if you get prompted that the folder you specified for the log does not exist)

When you want to start monitoring the process, right-click on the counter log and select Start (and later repeat but select Stop when you are ready to stop logging).


When you come to review the data, launch Perfmon and right-click on the graph then select Properties
Go to the Source tab and select Log files, then click Add
Browse to your .BLG file and add it, then click Apply
Select the Data tab and click Add - now you should only see all the processes that were running when you logged the data - find the instance(s) and counter(s) that are interesting and click Add for each, then Close

Click OK and you should see the logged information about the counter(s) selected - the default Y-axis is 0-100 so should work perfectly for percentage counters (for others you can manually the scale of the counter to make it fit, or the scale of the graph itself).


Hint: If you have multiple counters visible, use CTRL-H to highlight the selected one