From mboxrd@z Thu Jan 1 00:00:00 1970 From: NeilBrown Subject: Re: Data scribbling for raid6 is wrong? Date: Thu, 15 Dec 2011 15:27:23 +1100 Message-ID: <20111215152723.1d2bcca0@notabene.brown> References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/.DAPd5Bkc8_=H8jpPY50reT"; protocol="application/pgp-signature" Return-path: In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: Tao Guo Cc: linux-raid@vger.kernel.org List-Id: linux-raid.ids --Sig_/.DAPd5Bkc8_=H8jpPY50reT Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On Thu, 15 Dec 2011 11:15:42 +0800 Tao Guo wrote: > Hi all, >=20 > Today I checked the raid6's scribbling code, and I think there may be > some improvements to handle bad sectors: I think the common term is "scrubbing" rather than "scribbling". >=20 > If we have one bad sector(with corrupted data) in the data block, > scribbling thread will find parity mismatch and will try to > recompute&rewrite P&Q, but that will cause final data loss. > Since we have P & Q,=C2=A0 actually we can try to use them and find out t= he > wrong data block then fix it. >=20 > But the algorithm to find the bad data block seems not > straightforward... Does anyone know if there is any paper discussed > this issue before? >=20 > Update: I just found there is one talk about this in FAST08: > http://www.usenix.org/events/fast08/tech/krioukov.html. > But that approach will add checksums.etc. For bare-bones raid6, does > any guru have any better ideas? http://neil.brown.name/blog/20100211050355 NeilBrown --Sig_/.DAPd5Bkc8_=H8jpPY50reT Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (GNU/Linux) iQIVAwUBTul3Kznsnt1WYoG5AQIHvxAAs1OrcLmFOjdyEVN8ZYsawDT51CjT4qYt M7NLuZsNdx2A4BbYRXPRtkwdCzmAtzY+vzt4IEQyD8JBrg+MKPdqiUH8F3qpsPUT 4V/QNmcliPxP/zK9wLAklODoe/TMsk/jnKQ4hIOS+8LhEbzMp2lMMeYWYcmQt8+v 0gGmI0yjlNuVlO68C9Cdyezf+0OUGMn8uPn9YtWEy4CYl7yHmyRNNYHyct56Vljb 3lFcyFGtCne6mz17zvOdgzoo1gDBbPdY50hJhoFanuU/Tbf8sn2cUaKMLG4JJI5q TBGDBrcvLUNkHA7onTcZOsgX9MuVudDOY6Dsyh1gxsUGudRGIS2s9o2p6NRdleG4 ETKxwfCjD+fRc71+3DKxQ2PJEEP/AjGPrRHXpArU541yv+S00VWE9onHhTC9/LAg PP0IKZH5+xXmvfp9swl6mffHfjRvjn/t9t+TeQK9ex2Zb9M7AYWPBwdTn66GkgVb xWCRfLG0pRLpzICH3NVzFUQLpc1QxgqJIh4ixodtSVMZE7cmp56R3c19Co0q3Xlw fYZBG5UY9ExPjenMRpPO+g8mX3T0OBGiEIkcf7pSyiqm4R3Oba5eAmY/CSLfG6TP STkrY6qZWbNnmv5xHhdDM902Lgbm8KTj/y+4ajg7xE2djOmILchp44Alkk+EQv4J E44uYssTmHw= =Orl+ -----END PGP SIGNATURE----- --Sig_/.DAPd5Bkc8_=H8jpPY50reT--