xyzzy at speakeasy.org
Fri Mar 1 06:40:57 PST 2002
On Fri, 1 Mar 2002, Jakob Østergaard wrote:
> On Thu, Feb 28, 2002 at 06:52:42PM -0800, Trent Piepho wrote:
> > On Thu, 28 Feb 2002, Mark Hahn wrote:
> > > > Raid 5 is costly. As I understand it (not very well) there's 3 writes for
> > > > RAID 5. Reading can be slow, but not nearly as bad. Obviously you dont want
> > >
> > > I've never quite understood why people think R5 is expensive.
> > > yes, you have to do the parity calculation, and a 1 byte write
> > > does require an update of the parity block for that stripe,
> > > but it's not egregious.
> > In order to update a single RAID5 block you need to do two reads and two
> > writes.
> If you're writing not just one-bit-here-and-one-bit-there, but streaming
There is a difference between random writes and streaming writes. You are
correct that when doing streaming writes intelligent software can increase
speed by writing an entire cache stripe across all drives at the same time,
thus avoiding the read-modify-write cycle. But for random writes, the
read-modify-write cycle is still necessary, and I am not the slightest bit
wrong to say so.
More information about the Beowulf