SATA Error

[Zane C.B.]

On Thu, 8 Jun 2006 23:35:58 -0400
"Dave Stephens" <hsoftdev17 at gmail.com> wrote:

> OS Version:  FreeBSD 6.1
> 
> What appears to be repeated failures keep occurring with the SATA
> drive or controller in my server.    The error is a series of 3
> repeated messages where the only difference appears to be the offset
> and the LBA.  All of the hardware in this server is brand new and is
> not believed to be in faulty.  If anyone could tell me what is going
> on with this, or if it is a known issue point me at how I might patch
> something or otherwise fix it.  The server does not go down after the
> error, but the error is disconcerting none the less and leaves me
> worrying about hard drive data integrity.
> 
> Sample Error Message......
> --------------------------------------------------
> 
> g_vfs_done() : ad8s4e[WRITE(offset=59959787520, length=131072)]error=5
> ad8: TIMEOUT - WRITE_DMA48 retrying (1 retry left) LBA=xxxxxxxxxxx
> ad8: FAILURE - WRITE_DMA48 status=51 <READY,DSC,ERROR> error=10
> <NID_NOT_FOUND> LBA=xxxxxxxxxxx
> 
> 
> Here is some related info cut out of dmesg.....
> 
> SATA Drive
> --------------------------------------------------------------------------------
> ad8: 286168MB <Seagate ST3300822AS 3.AAD> at ata4-master SATA150
> 
> SATA Controllers
> --------------------------------------------------------------------------------
> atapci1: <SiS 180 SATA150 controller> port
> 0xeff0-0xeff7,0xefe4-0xefe7,0xefa8-0xefaf,0xefe0-0xefe3,0xef
> 90-0xef9f irq 17 at device 5.0 on pci0
> ata2: <ATA channel 0> on atapci1
> ata3: <ATA channel 1> on atapci1
> atapci2: <SiI 3112 SATA150 controller> port
> 0xefa0-0xefa7,0xef8c-0xef8f,0xef80-0xef87,0xef88-0xef8b,0xe
> f60-0xef6f mem 0xfebfac00-0xfebfadff irq 17 at device 9.0 on pci0
> ata4: <ATA channel 0> on atapci2
> ata5: <ATA channel 1> on atapci2
> 
> Note that atapci1 is built onto the motherboard and doesn't seem to be
> supported by FreeBSD at this time (no HDDs can be found during install
> when they are attached to it.)

The SiI 3112 is very flaky. I suggest going with a highpoint. I do not
know about the SiS chip there.