On Tue, Oct 22, 2002 at 11:58:56AM +0200, raid@ddx.a2000.nu wrote:
> On Tue, 22 Oct 2002, Chris Siebenmann wrote:
> > At a guess: when RAID-5 is intact, the kernel must read the entire
> > stripe size worth of data to verify the parity. When a RAID-5 array has
> > a dead disk, any intact data block can be handed to the application
> > the moment it comes off the disk as there is no point in doing parity
> > verification. (The kernel has to reconstruct the missing blocks, but
> > most of the blocks are present and good.)
>
> i thought raid5 was doing parity calculation when writing ?
Correct. RAID-5 will not do parity calculation when reading. RAID-5 will
give you availability but it will not give you integrity.
> difference between rading from failed an intact raid5 is almost twice the
> speed (failed is doing 150MB/sec, intact is doing 80MB/sec)
I didn't follow the beginning of this thread, sorry. Is this SCSI?
--
................................................................
: jakob@unthought.net : And I see the elder races, :
:.........................: putrid forms of man :
: Jakob Østergaard : See him rise and claim the earth, :
: OZ9ABN : his downfall is at hand. :
:.........................:............{Konkhra}...............:
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
