** This is the quasi-official and semi-temporary T13 email list server. **
[EMAIL PROTECTED] said:
>May I make a suggestion? As in the ATA6 AV Feature Set
>proposal a good definition of the command completion time
>would be the time from the command register being
>written to the last interrupt of the last sector transferred.
That sounds like the definition that has been used for the last 50
years to measure command execution time.
>This allows true device performance to be measured, but requires
>that the IDE driver, and associated structure includes a mechanism
>to transfer the times beyond the kernel. This is highly OS specific, I
>know, but it is the only true way to HDD performance without dedicated
>hardware.
Most hard disk performance measurement is by strange and poorly
designed applications programs written by people that (in my
experience and my opinion) really do not understand what they are
doing and what they are trying to measure. An OS that had some device
driver interface that returned the command execution time would
certainly lead to even more of this software.
>At Philips we have modified the request structure to include a Start
>Time and a Finish Time for a request. In such a way very accurate
>HDD performance can be measured, such as head & track skews,
>for example.
But do you also return the time from the end of the previous command
to the beginning of the command that was just executed? If you are
not measuring that time then, I'm sorry, you are missing the SINGLE
MOST IMPORTANT THING THAT AFFECTS HARD DISK DRIVE PERFORMANCE,
ESPECIALLY CACHING PERFORMANCE.
*** Hale Landis *** [EMAIL PROTECTED] ***
*** Niwot, CO USA *** www.ata-atapi.com ***
--
If you have any questions or wish to unsubscribe send a
message to Hale Landis, [EMAIL PROTECTED] To post to
this list server send your message to [EMAIL PROTECTED]
For questions concerning Thistle Grove Industries or TGI's
list services please send email to [EMAIL PROTECTED]
