From mboxrd@z Thu Jan 1 00:00:00 1970 From: Loic Dachary Subject: Re: Comments on Ceph distributed parity implementation Date: Sun, 16 Jun 2013 23:31:29 +0200 Message-ID: <51BE2EB1.2020807@dachary.org> References: <20130614201327.70240@gmx.com> <51BB9FC3.8040102@dachary.org> <622F4407872BA447A16110F65453358C01A4D3D29CB3@FMSAMAIL.fmsa.local> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigA2A3C90E76481DCCA04A8C21" Return-path: Received: from smtp.dmail.dachary.org ([86.65.39.20]:59476 "EHLO smtp.dmail.dachary.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750847Ab3FPVbd (ORCPT ); Sun, 16 Jun 2013 17:31:33 -0400 In-Reply-To: Sender: ceph-devel-owner@vger.kernel.org List-ID: To: =?ISO-8859-1?Q?Beno=EEt_Parrein?= Cc: ceph-devel@vger.kernel.org, "James S. Plank" This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigA2A3C90E76481DCCA04A8C21 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Hi Beno=EEt, =46rom the ( na=EFve ) point of view of engineering, performances are imp= ortant. The recent works of James Plank ( cc'ed ) greatly improved them and I'm looking forward to the next version of jerasure ( http://web.eec= s.utk.edu/~plank/plank/papers/CS-08-627.html ). Rozofs Mojette Transform = implementation ( https://github.com/rozofs/rozofs/blob/master/rozofs/comm= on/transform.h & https://github.com/rozofs/rozofs/blob/master/rozofs/comm= on/transform.cc ) does not seem to make use of SIMD. Is it because the pe= rformances are good enough to not require them ? Cheers On 06/16/2013 09:51 PM, Beno=EEt Parrein wrote: > Paul Von-Stamwitz us.fujitsu.com> writes: >=20 > Hi Paul,=20 >=20 >> >> Loic, I know nothing about Mojette Transforms. From what little I glea= ned,=20 > it might be good for repair >> (needing only a subset of chunks within a range to recalculate a missi= ng=20 > chunk) but I'm worried about the >> storage efficiency. RozoFS claims 1.5x. I'd like to do better than tha= t. >> >> All the best, >> Paul >> >=20 > If you want to do better than that you will probably lose in availabili= ty.=20 > 1.5x give the same availability than 3 replicats and that for any kind = of=20 > erasure coding. > FYI, Mojette transform has no constraint in terms of Galois fields. It = is the=20 > big advantage to use discrete geometry rather than algebra. >=20 > best regards, > bp >=20 >=20 >=20 > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" i= n > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html --=20 Lo=EFc Dachary, Artisan Logiciel Libre All that is necessary for the triumph of evil is that good people do noth= ing. --------------enigA2A3C90E76481DCCA04A8C21 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAlG+LrEACgkQ8dLMyEl6F20JbACdErjMvLzvIr4tLUcajL22FqtI 1J0AnRDAHpU6DE8wcHoEMzFqZJTAiQ7j =K1I4 -----END PGP SIGNATURE----- --------------enigA2A3C90E76481DCCA04A8C21--