[EMAIL PROTECTED] wrote:
>
> On Fri, May 21, 1999 at 06:13:12PM +0200, Dietmar Stein wrote:
> > Hi
> >
> ...
> > Readperformance will only increase by using raid0 (stripe), but it will
> > not be twice times faster.
>
> Not quite true.
>
Hm, I thought of the theory which is used for SMP machines; you got two
cpus but you got not double performance.
In theory you have double performance by using double cpus, and double
read performance by using striped disks (two disks), but practice shows
that you have not.
Nethertheless (I read about raid1) and know, that raid1 also "stripes"
reads and therefore it increases read performance.
> raid-1 also increases read performance. It can do reads just like raid0,
> because both disks contain the same data. It doesn't read the same block
> from both disks and compare, instead it reads like from a stripe set (raid0).
>
> At least that's the theory. Your points about several drives on the same
> bus etc. are ofcourse valid. If two IDE disks are put on _separate_ busses
> and the IDE chipset doesn't stink too much, you should see good read performance
> both from raid0 and raid1.
>
Yeah - using the two disks on separate controllers will increase
performance of course. I suggested he is using both disks on the same
controller (was a mistake, because he uses /dev/hda and /dev/hdd for the
mirror, which are of course on separate controllers).
Greetings, Dietmar
> ................................................................
> : [EMAIL PROTECTED] : And I see the elder races, :
> :.........................: putrid forms of man :
> : Jakob �stergaard : See him rise and claim the earth, :
> : OZ9ABN : his downfall is at hand. :
> :.........................:............{Konkhra}...............:
--
[EMAIL PROTECTED] [EMAIL PROTECTED]
Systemadministrator UNIX / Linux
