vinum and hot-swapping

[Malcolm Kay]

On Sun, 13 Jul 2003 19:15, Andrea Venturoli wrote:
> ** Reply to note from "Greg 'groggy' Lehey" <grog at freebsd.org> Sat, 12 Jul
> 2003 17:13:29 +0930
>
> > The real performance penalty for RAID-5 is simply that writes require
> > so much I/O.  Expect 25% of the write performance of RAID-0.
>
> Ok, I must ask this:
> Shouldn't SCSI system allow paralell writes on different disks?

Physical writes yes. But how does the data get there?
The SCSI bus (like any other) has a finite bandwidth.

But maybe if you are very clever you can coax the SCSI bus into
transmitting the same information to all disks in parallel.

> If so, why so much penalty?

Malcolm Kay