Re: RAID-3? (was: cvs commit: src MAINTAINERS)

From: Pawel Jakub Dawidek (pjd_at_FreeBSD.org)
Date: 08/21/04

  • Next message: Pawel Jakub Dawidek: "Re: RAID-3? (was: cvs commit: src MAINTAINERS)" 
    Date: Sat, 21 Aug 2004 10:37:57 +0200
To: Greg 'groggy' Lehey <grog@FreeBSD.org>

    On Sat, Aug 21, 2004 at 06:02:07PM +0930, Greg 'groggy' Lehey wrote:
    +> On Saturday, 21 August 2004 at 10:06:14 +0200, Pawel Jakub Dawidek wrote:
    +> > So as you can see there are no difference in reading (actually
    +> > reading in degraded mode is even a bit faster, hard to say why).
    +>
    +> I would have half expected this. If you're reading parity as well,
    +> then without spindle sync it will take longer for three I/Os to
    +> complete than 2.

    I'm not sure if I understand you well...
    In RAID3, when array is complete you don't use parity component for
    reading at all. So in complete mode, as well as in degraded mode RAID3
    is using only two components for reading. 

    -- 
Pawel Jakub Dawidek                       http://www.FreeBSD.org
pjd@FreeBSD.org                           http://garage.freebsd.pl
FreeBSD committer                         Am I Evil? Yes, I Am!

  • Next message: Pawel Jakub Dawidek: "Re: RAID-3? (was: cvs commit: src MAINTAINERS)"

    Relevant Pages

    • Re: RAID-3? (was: cvs commit: src MAINTAINERS)
      ... a misassumption. ... as well as in degraded mode ... > RAID3 is using only two components for reading. ... Finger grog@FreeBSD.org for PGP public key. ...
      (freebsd-performance)
    • Re: RAID-3? (was: cvs commit: src MAINTAINERS)
      ... > reading in degraded mode is even a bit faster, ... Greg ... I discard all HTML mail unseen. ...
      (freebsd-performance)
    • Re: RAID-3? (was: cvs commit: src MAINTAINERS)
      ... so parity component can be also ... and you would also be touching all of the data with the CPU. ... Those are results from RAID3 test without one data component, ... So as you can see there are no difference in reading (actually reading ...
      (freebsd-performance)