Re: Corruption Stats (fwd)

Stefan Traby (stefan@sime.com)
Fri, 31 Jul 1998 00:45:05 +0200


Hi Gerard !

> > BTW: A drive following the SCSI-specs may cause disk-corruption
> > under Linux (WCE=1). Data may still be in write-cache after
> > shutdown and power-off. (I miss "synchronize cache").
> > This is for shure a theoretical problem, but a practical bug.
> > Or did I miss something ?
>
> Synchronizing the cache of real hard disks isn't worth it since
> they have a small cache compared to their data transfer speed, so
> the risk is minimal unless you are rather a hurry penguin each

A SCSI-conform random access device doesn't need to flush to the
physical media if WCE=1 is enabled __before__ a "synchonize cache"
SCB is executed. So it is worth thinking about it.
After shutdown we may loose the full wrt-cache contents
if the drive does not perform an auto-flush, because unwritten data
may stay unwritten in disk cache forever.
Ok, let's close the thread, I rename scsi.c to scsi_like.c and
can live with it, why care about standards at all.

-- 
  ciao - 
    Stefan

Stefan Traby phone: +43-3133-6107-2 Mitterlasznitzstr. 13 fax: +43-3133-6107-9 8302 Nestelbach mailto://stefan@sime.com Austria

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html