[no subject]

00702132154.l1DLsAfI042441@apollo.backplane.com> <1a00a5aa0702141513t42a9e2d1qf441bc1b74e66824@mail.gmail.com>
From: "Simon 'corecode' Schubert" <corecode@fs.ei.tum.de>
Subject: Re: Plans for 1.8+ (2.0?)
Date: Thu, 15 Feb 2007 01:49:34 +0100
BestServHost: crater.dragonflybsd.org
List-Post: <mailto:kernel@crater.dragonflybsd.org>
List-Subscribe: <mailto:kernel-request@crater.dragonflybsd.org?body=subscribe>
List-Unsubscribe: <mailto:kernel-request@crater.dragonflybsd.org?body=unsubscribe>
List-Help: <mailto:kernel-request@crater.dragonflybsd.org?body=help>
List-Owner: <mailto:owner-kernel@crater.dragonflybsd.org>
MIME-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-sha1;
 protocol="application/pgp-signature";
 boundary="------------enigA380427F70255373A4AA63FC"
In-Reply-To: <1a00a5aa0702141513t42a9e2d1qf441bc1b74e66824@mail.gmail.com>
Sender: kernel-errors@crater.dragonflybsd.org
Errors-To: kernel-errors@crater.dragonflybsd.org
Lines: 58
NNTP-Posting-Host: 216.240.41.25
X-Trace: 1171501305 crater_reader.dragonflybsd.org 833 216.240.41.25
Xref: crater_reader.dragonflybsd.org dragonfly.kernel:10610

This is an OpenPGP/MIME signed message (RFC 2440 and 3156)
--------------enigA380427F70255373A4AA63FC
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: quoted-printable

Chris Csanady wrote:
> Yes, I was considering it as a replacement for RAID-5.  The idea being
> that, for a given filesystem block, you would divide it into
> sub-blocks and compute ECC blocks.  These would then be distributed
> across the cluster nodes.
>=20
> For example, consider a 32kB filesystem block.  Divide it into 4kB
> sub-blocks, and compute 3 4kB ECC blocks.  Now, distribute those 11
> blocks over 11 separate nodes.  Any three nodes can fail, plus space
> overhead is only 38% in this case.  To provide the same guarantee with
> mirroring would carry a 300% overhead.  While mirroring may be
> acceptable in terms of disk space, network I/O will likely be a
> problem.

How do you save on network IO there?  You have to query 8(!) boxes to ret=
rieve one block.  Okay, you might choose 8 out of 11, but that's still a =
lot.  For writing, you of course have to write to all 11.  If you go mirr=
oring, you can run the complete block from one source (you can of course =
also interleave with a mirror).  For writing, you can use multicast/broad=
cast on LAN.  That makes mirrored writes as efficient as normal writes.  =
When you do ECC, you have to write all 138%.  If you run over WAN, you wo=
n't be able to save with multicast probably, but then your block distribu=
tion will make it really hard to get a constant stream due to massive jit=
ter.

I'm not yet convinced :)  Disk space is really cheap these days.

cheers
  simon

--=20
Serve - BSD     +++  RENT this banner advert  +++    ASCII Ribbon   /"\
Work - Mac      +++  space for low =E2=82=AC=E2=82=AC=E2=82=AC NOW!1  +++=
      Campaign     \ /
Party Enjoy Relax   |   http://dragonflybsd.org      Against  HTML   \
Dude 2c 2 the max   !   http://golden-apple.biz       Mail + News   / \


--------------enigA380427F70255373A4AA63FC
Content-Type: application/pgp-signature; name="signature.asc"
Content-Description: OpenPGP digital signature
Content-Disposition: attachment; filename="signature.asc"

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.3 (DragonFly)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org

iD8DBQFF064ir5S+dk6z85oRApErAKDetBgHH6DKkYN+BIcC2eZHXVcrbwCgpRND
ZmvEd5EpbFx2NlY/2x+c7q0=
=9YCD
-----END PGP SIGNATURE-----

--------------enigA380427F70255373A4AA63FC--