From mboxrd@z Thu Jan 1 00:00:00 1970 From: Loic Dachary Subject: Re: v2 aligned buffer changes for erasure codes Date: Fri, 19 Sep 2014 11:18:40 +0200 Message-ID: <541BF4F0.4000203@dachary.org> References: <1410796508-28711-1-git-send-email-j@jannau.net>,<1411036435-18860-1-git-send-email-j@jannau.net>,<3472A07E6605974CBC9BC573F1BC02E4AE7D1265@CERNXCHG44.cern.ch> <3472A07E6605974CBC9BC573F1BC02E4AE7D13BB@CERNXCHG44.cern.ch> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="GrRkS8TnPIL0IveVJ1PIcI5pumBO2pR9H" Return-path: Received: from mail2.dachary.org ([91.121.57.175]:55681 "EHLO smtp.dmail.dachary.org" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751668AbaISJSq (ORCPT ); Fri, 19 Sep 2014 05:18:46 -0400 In-Reply-To: <3472A07E6605974CBC9BC573F1BC02E4AE7D13BB@CERNXCHG44.cern.ch> Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Andreas Joachim Peters , Janne Grunau , "ceph-devel@vger.kernel.org" This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --GrRkS8TnPIL0IveVJ1PIcI5pumBO2pR9H Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Hi Andreas, The per_chunk_alignment addresses a backward compatible change in the way= they are calculated. The problem was that the initial calculation lead t= o oversized chunks. The long explanation is at https://github.com/ceph/ce= ph/commit/c7daaaf5e63d0bd1d444385e62611fe276f6ce29 Please let me know if you see something wrong :-) Cheers On 18/09/2014 14:34, Andreas Joachim Peters wrote: > Hi Janne/Loic,=20 > there is more confusion atleast on my side ... >=20 > I had now a look at the jerasure plug-in and I am now slightly confused= why you have two ways to return in get_alignment ... one is as I assume = and another one is "per_chunk_alignment" ... what should the function ret= urn Loic? >=20 > Cheers Andreas. > ________________________________________ > From: ceph-devel-owner@vger.kernel.org [ceph-devel-owner@vger.kernel.or= g] on behalf of Andreas Joachim Peters [Andreas.Joachim.Peters@cern.ch] > Sent: 18 September 2014 14:18 > To: Janne Grunau; ceph-devel@vger.kernel.org > Subject: RE: v2 aligned buffer changes for erasure codes >=20 > Hi Janne, > =3D> (src/erasure-code/isa/README claims it needs 16*k byte aligned buf= fers >=20 > I should update the README since it is misleading ... it should say 8*k= or 16*k byte aligned chunk size depending on the compiler/platform used,= it is not the alignment of the allocated buffer addresses.The get_alignm= ent in the plug-in function is used to compute the chunk size for the enc= oding (as I said not the start address alignment). >=20 > If you pass k buffers for decoding each buffer should be aligned at lea= st to 16 or as you pointed out better 32 bytes. >=20 > For encoding there is normally a single buffer split 'virtually' into k= pieces. To make all pieces starting at an aligned address one needs to a= lign the chunk size to e.g. 16*k. For the best possible performance on al= l platforms we should change the get_alignment function in the ISA plug-i= n to return 32*k if there are no other objections ?!?! >=20 > Cheers Andreas. > ________________________________________ > From: ceph-devel-owner@vger.kernel.org [ceph-devel-owner@vger.kernel.or= g] on behalf of Janne Grunau [j@jannau.net] > Sent: 18 September 2014 12:33 > To: ceph-devel@vger.kernel.org > Subject: v2 aligned buffer changes for erasure codes >=20 > Hi, >=20 > following a is an updated patchset. It passes now make check in src >=20 > It has following changes: > * use 32-byte alignment since the isa plugin use AVX2 > (src/erasure-code/isa/README claims it needs 16*k byte aligned buffe= rs > but I can't see a reason why it would need more than 32-bytes > * ErasureCode::encode_prepare() handles more than one chunk with paddi= ng >=20 > cheers >=20 > Janne > -- > 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 > -- > 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 > -- > 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 --=20 Lo=EFc Dachary, Artisan Logiciel Libre --GrRkS8TnPIL0IveVJ1PIcI5pumBO2pR9H Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iEYEARECAAYFAlQb9PAACgkQ8dLMyEl6F21f4gCfZZVQyr9MiupvcjreGZsiS1f/ anYAn2KeO64MxEVmfQV8zeHrXMe/stxG =nV4T -----END PGP SIGNATURE----- --GrRkS8TnPIL0IveVJ1PIcI5pumBO2pR9H--