Re: [PATCH][INCOMPLETE] sata_nv: merge ADMA support

["Bill Rugolsky Jr." <bill@rugolsky.com>]

On Sun, Mar 26, 2006 at 08:14:35PM -0500, Matt Heler wrote:
> Using Bill's original patch I was able to boot up perfectly with adma support 
> enabled on my workstation. Even after several stress tests ( 
> tar -cf /dev/null . , and dd if=/dev/sda of=/dev/null ), everything seems to 
> be a-ok. However when I tried the sata_nv.c file that you sent to Bill, I 
> kept on getting hardlocks, and thus was unable to stress test your version. 
> 
> Also for note, I heve not received any of the timeout problems reported by 
> Bill. Nor have I had any latency problems with adma enabled.
 
Matt,

Nice to see some value falling out of this sata_nv thread.  Did you see
latency problems before enabling ADMA?

Would you provide some specifics on your setup?

Which motherboard, #CPUs, BIOS revision, kernel, MD/LVM2/fs?

On two of my Tyan S2895 machines, including the one that I'm using for testing,
lspci says:

00:06.0 IDE interface: nVidia Corporation CK804 IDE (rev f2)
00:07.0 IDE interface: nVidia Corporation CK804 Serial ATA Controller (rev f3)
00:08.0 IDE interface: nVidia Corporation CK804 Serial ATA Controller (rev f3)

and dmidecode says:

BIOS Information
        Vendor: Phoenix Technologies Ltd.
        Version: 2004Q3
        Release Date: 10/12/2005

The other, where I first had lost tick problems, says:

00:06.0 IDE interface: nVidia Corporation CK804 IDE (rev a2)
00:07.0 IDE interface: nVidia Corporation CK804 Serial ATA Controller (rev a3)
00:08.0 IDE interface: nVidia Corporation CK804 Serial ATA Controller (rev a3)

BIOS Information
	Vendor: Phoenix Technologies Ltd.
	Version: 2004Q3
	Release Date: 06/07/2005


Thanks,

	Bill