• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

99% CPU when accessing a disk

I have a file server with 4 disks on the MB IDE interface, and 2 seperate PCI IDE controllers.

I noticed some general system annoyances (mainly horrific transfer speeds) and used HD Tack to track down that one of the drives on one of the PCI cards was having 99% CPU utilization and had a transfer speed of something like 2MB/s!!

What I want to do is ensure that UDMA is enabled for the PCI cards, but I don't know how to do this (for the MB IDE controller you can simply use device manager). I also used SiSoft because I know that it might be able to do this, but while it recognises all of the HDDs, it will only show details analysis of the onboard IDE controller. So my 2 questions are:

1) How can I make sure that UDMA is working for the PCI cards
2) What else could cause 99% cpu utilization? Could it be a broken disk?

What I will have to do, I suspect, is move the disk onto a different channel/machine to test, but any guidance from you guys would be brilliant.

Thanks

Simon
 
Do you have the drivers for the PCI cards installed ? Are there newer drivers available on the manufacturers site, or even the site of the chipset maker ?

I would think that through the Device Manager you would be able to find something in the the PCI devices to check for the DMA setting.

My best guess is a driver issue at this point.

 
Update:

I rebooted the file server and re-ran HD Tach on the drive and the CPU utilization was fine and the through was fine. Decided to try and copy all the files off the disk to try and get as much of a backup as possible.

At a certain file the copy stopped and just sat there. I cancelled it after a while and re-ran HD Tach and got the previous bad results. So, it looks as though the disk had a dodgy are and Windows isn't handling it very well as its clogging up the OS even after the copy has been cancelled.

Going to run Maxtor's PowerMax on it to try and see. if there's some bad sectors and if they can be cordoned off.
 
Aye, I should maybe have mentioned that when I noticed odities with the system, that I tried chkdsk. I wasn't being very meticulous about it, but I know that it was all going well until one 'stalled' and then after that the next one stalled and I gave up with it. I assume now that its the same problem, windows getting bogged down with whatever this is and causing all subsequent IDE ops to grind.

Gonna run PowerMax in 5 minutes, will post results.
 
oh well. PowerMax said the drive was failing and needed to be replaced. And wouldn't you know it, out of warranty by 2 months!

Must have been something pretty serious, like mechanical or a substrate issue.

Case closed.
 
Sometimes you can get some life with a low-level format, but as cheap as drives are these days it's probably best to just get a new one.

 
Back
Top