[stgt] [BUG] Tgt-1.0.8 exited unexpectedly

Hirokazu Takahashi taka at valinux.co.jp
Sat Oct 2 00:05:06 CEST 2010


> > > > > I'm not sure the modern SATA disk can detect such failure.
> > > > 
> > > > I think the modern SATA disk has this feature while the IDE disk doesn't
> > > > have.
> > > 
> > > Do you have any pointer?
> > 
> > This may help you:
> > http://www.seagate.com/content/pdf/whitepaper/SerialATA_comparison_UATA_Technology.pdf
> > It says serial ATA adds 32-bit CRC error correction for all bits transmitted,
> > as opposed to only data packets in Ultra ATA.
> > And it is known that each sector of modern disks has extra bits for ECCs to
> > correct errors.
> Hmm, this isn't same as what SCSI DIF (and enterprise storage) does to
> prevent silient data corruption. This handles only transmission
> corruption. So there is still a good chance that silient data
> corruption could happen.
> SCSI DIF and enterprise storage maintain extra bytes per sector for
> checksumming to prevent silient data corruption.

I guess SCSI DIF is a feature which adds extra bytes to each sector
and its protocol allows software to control them.

I think each sector has another extra field which SCSI or SATA drives
internally use to correct errors.

> > I think you can find the details in the specification of serial ATA if you
> > have a right to access it.
> I heard that SATA committee considered to add something like SCSI DIF
> to SATA spec last year. I'm not sure if it was accepted.
> --
To unsubscribe from this list: send the line "unsubscribe stgt" in
the body of a message to majordomo at vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

More information about the stgt mailing list