• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

high cpu utilization in hd tach

aznkid83

Limp Gawd
Joined
Mar 14, 2001
Messages
158
i have two mobo's that use the kt133a chipset with the 686b southbridge. one is the abit kt7a v1.3, the other is the msi k7t turbo-r limited edition. in both computers, running windows xp pro, i used hdtach 2.61 and get about 30% cpu utilization and about 66 MB/s burst. after tweaking the pci settings in the msi board i got it down to 20% cpu utilization and hitting 70 to 75 MB/s burst rate. i saw the same improvement using the built in promise ata100 controller. all drives are 7200 rpm with 8MB cache and are ata/100 and ata/133. i also installed george breese's pci latency patch version 0.20 build 21 just before i started tweaking the pci settings. i saw very little improvement. if anyone has any insight on this, please help me. thanks
 
i had the same problem with that motherboard. i have a feeling that it's just the VIA PCI latency issue causing problems.
 
Originally posted by dewhite
20% seems relatively good for using onboard controllers...

It's unfortunately quite typical but nowhere near good. For example the IDE controllers on my old P4T533-C i850e (2.4a/533mhz) mobo and the SATA controllers on my Asus P4S800D-E Deluxe (2.8C/800mhz) show CPU utilization in the 2-4% range. The CPU utilization is not only affected by the controllers themselves, but also various latency issues, FSB speed and CPU speed given a constant controller overhead the more work done by the CPU the lower the percentage of that total work that is dedicated to the controller overhead.
 
i had a promise card one time and it too gave similar results. but is this percentage indicative of real world cpu usage? glad i'm not the only one seeing 20% numbers
 
Back
Top